Expand the sub-agent bullet to push fan-out work (many files,
parallel searches, multi-point checks) to sub-agents rather than
serial iteration, and default to delegation for multi-file
exploration. Counters Opus 4.8's tendency to under-delegate.
Co-Authored-By: Claude <noreply@anthropic.com>
Drop the top-level "model" key so the session falls back to the
default model instead of forcing claude-fable-5[1m].
Co-Authored-By: Claude <noreply@anthropic.com>
Fable 5 audit of the global CLAUDE.md (symlinked from this repo):
Contradictions resolved:
- two conflicting graphify sections merged into one (query-first when
graphify-out/graph.json exists, direct read otherwise; single command
form; dropped the false 'this project has a knowledge graph' claim)
- plan rule: 'when in doubt skip plan' no longer cancels the mandate —
borderline = single-file small obvious change
- deviation rule disambiguated: minor/justified -> explain after,
significant/shaky -> ask before
- 'append-only' registries reconciled with /prune-memory curation
Dead refs fixed: /caveman:compress -> /caveman-compress; design-gate
path now ~/.claude/lib/ (was repo-relative); '(replaces LESSONS)' note
dropped.
Structure: Health Stack / Skill routing / graphify no longer nested
under '# Communication mode'; new '# Tooling & skills' and
'# This repo only' sections; repo-specific Health Stack labeled as such.
Routing updated: + audit-delta, close, capitalize, prune-memory,
profile, context-restore, geo; explicit gstack-OFF fallback rule.
Mid-task question exception generalized to all skill-mandated gates.
Non-critical sections caveman-compressed; Architecture decisions and
Security kept verbatim (must stay unambiguous). Net -1471 chars while
adding 8 routing entries.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Both blind judges flagged the same residual: without a detection
criterion, a /seo-dispatched subagent could misread itself as headless
and degrade to report-only. Unreachable = no answer obtainable at all
(cron/CI, user explicitly absent); orchestrator dispatch with a main
thread that can relay questions is reachable.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
readme-updater.md does not exist on disk; STEPs 5b and 12 were broken
references. doc-syncer.md AUTO MODE covers both cases (README bootstrap
when missing, drift sync after changes).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
"Update project memory" instructed file writes while RULES say
"Do not modify files". Patterns now surface in the analysis output;
persistence stays in the main thread via the gated capitalize flow.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Live darwin test: with the user unreachable, the triage table's
"Confirmation: No" batches edited 2 source HTML files unsupervised.
Autonomous batches presume a reachable user who saw the printed plan;
headless -> all batches report-only with ready-to-apply content.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Round 2 of darwin optimization (judge-identified residuals):
- 3c marker rule now cross-references the STEP 0 dangling/corrupted
exceptions instead of contradicting them
- corrupted-but-present state JSON branch defined (trust no axis,
ask repair/reset; headless -> full codebase report-only, file as-is)
- unreachable user at 3e max-cycles STOP -> fail closed: revert axis
fixes, findings back to open, marker untouched
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Round 1 of darwin optimization, dim3 (failure-mode encoding). Live test
showed two agents diverging on undefined branches:
- dangling marker + unreachable user -> now full-codebase report-only,
marker untouched (corrupted state needs user-approved repair)
- no axes named + unreachable user -> now defaults to all four axes
Also adds the matching Common-mistakes row. Includes test-prompts.json.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Update the gstack submodule pin 026751e -> 070722a (v1.52.1.0: brain-aware planning + memory diagnostic + CDP leak fixes). Also removed a junk recursive self-symlink (bin/bin -> bin) from the submodule working tree.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Wrap the frontmatter description in quotes (defensive valid-YAML: it contains an em-dash and an apostrophe). Add skills/design-motion-principles to the external-skill-symlink ignore allowlist so it matches its 4 siblings (emil-design-eng, frontend-design, darwin-skill, find-skills) and stops surfacing as untracked noise — consistent with the LRN-025 allowlist rule.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Strip the disable-model-invocation frontmatter key from all 19 editable skills. Absent = default = model invocation enabled. 8 were 'true' and blocked the model AND orchestrators from self-routing (status, plugin-check, analyze, onboard, refactor, init-project, pdf-translate, ship-feature) — contradicting the CLAUDE.md skill-routing rules. The other 11 were 'false', a no-op noise line.
The setting is binary (no per-caller granularity), so enabling orchestrator chaining also enables model auto-fire — accepted. Genuinely destructive operations remain guarded by the careful/guard hooks, independent of this flag.
Capitalized: BDR-019 (decision), LRN-026 (learning), journal 2026-06-09.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Salvages registry-worthy insights from the conversation before /clear or /compact wipes context. Scans the conversation, dedups each candidate against the existing .claude/memory/ registries (its signature move vs /close), routes across all 5 registries behind a compact approval gate, always writes a journal line.
Baseline-tested per superpowers:writing-skills (RED/GREEN/REFACTOR): the no-skill baseline double-logged one incident across LRN+BLK; the skill passes clean and now counters that via a 'one incident -> one primary registry' rule. Ships v1 with the approval gate as the human safety net (same posture as /prune-memory).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A gstack submodule bump added `spec` (v1.47) and the iOS device-farm
5-skill set (v1.43) but gstack `./setup` was never re-run, leaving all 6
as source-only — unlinked, invisible to Claude and untouched by
reset/`gstack on`.
- Link `spec` only, surgically: skills/spec/SKILL.md symlink matching
gstack setup's per-skill pattern (real dir + absolute SKILL.md link).
Platform-agnostic, useful planning skill. Added to full + web-full
profiles (must be in the active `full` profile or `set full` would
re-disable it).
- iOS skills deliberately NOT linked: this is a Linux host, and the iOS
device-farm needs a Mac daemon + Tailscale + physical iOS devices.
Linking them would add 5 dead skills plus passive token cost.
- Complete the .gitignore gstack allowlist: add the 12 entries missing
from it — `spec`, the 5 `ios-*` (so they stay ignored if a future
setup on a Mac materializes them), and 6 already-parked skills
(document-generate, landing-report, scrape, setup-gbrain, skillify,
sync-gbrain). The parked ones matter because `gstack on` moves parked
skills into skills/, where any allowlist gap becomes untracked git
noise. Also drop the stale `skills/checkpoint` entry (renamed to
context-save).
Verified: `profile show full`/`web-full` report spec enabled; the
source-vs-allowlist drift check is now empty; profile.sh still parses.
The gstack submodule pointer bump itself is left uncommitted (separate
pending work).
Memory: BLK-007 -> resolved; LRN-025 (gitignore allowlist must cover all
toggleable skills incl. parked, else enabling one = git noise).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Centralize gstack toggling in the `profile` command without losing the
active-profile label.
- `gstack on` re-enables ALL parked gstack skills (moves
skills-disabled/gstack__* back) but does NOT touch .active-profile,
so the user layers full gstack on top of their current profile and
the statusline label is preserved. Unlike `reset`, which clears the
label to "none".
- `gstack off` disables gstack skills not listed in the active profile;
errors cleanly when no profile is active (needs one to know what to
keep).
Refactor (behavior-preserving): extract three shared helpers
`enable_all_gstack`, `disable_gstack_not_in`, `parked_gstack_count` and
rewire `cmd_reset` + `cmd_set` to reuse them instead of duplicating the
symlink-toggle loops. Wire `gstack` into main() dispatch, usage(), and the
header usage block.
Docs: SKILL.md argument-hint, examples, and output-policy updated. The
generic `make profile cmd="gstack on"` target already covers Make usage.
Verified: shellcheck CLEAN, `bash -n` OK, 6-case test (help, bad-action,
off-with-no-profile, on, off-trim, on-cycle) with final assertion that the
live symlink state was restored exactly to its pre-test value.
Memory: capitalize BDR-018 (decision), LRN-024 (DRY helper-extraction
pattern), BLK-007 (6 gstack source skills ios-*/spec unlinked post
submodule bump — open follow-up), EVAL-002 (self-eval, false "full.profile
bug" flag corrected pre-edit). Backfill index drift: BDR-017, BLK-005/006.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a tiered-by-scope "Design work — full toolchain" rule to the global
CLAUDE.md: trivial tweaks stay on /hotfix, building UI mobilizes ui-ux-pro-max,
frontend-design, Magic MCP, emil-design-eng, design-motion-principles, and
design-html; design systems start with design-consultation; reviews use
design-review + emil + motion audit. In doubt about scope, do not silently
skip the toolchain — ask or default to the Build tier.
Reinforce it with a design-toolchain-reminder UserPromptSubmit hook that
detects UI/design signals (broad FR+EN keyword set, \b-guarded against
substring false matches) and injects the tiered guidance into context. Soft
nudge, always exits 0, falls back to raw stdin when the hook JSON is missing.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The gstack/bin/ and gstack/browse/dist/ symlinks (added in link.sh) were
missing from install-plugins.sh and update-all.sh, meaning fresh installs
and updates wouldn't create them. Also adds doctor.sh health checks.
- install-plugins.sh: create symlinks after gstack ./setup
- update-all.sh: refresh symlinks after gstack submodule update
- doctor.sh: verify both symlinks exist in consistency section
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Per-skill SKILL.md symlinks don't expose gstack's shared infrastructure.
Multiple skills hardcode ~/.claude/skills/gstack/bin/ (gstack-config,
gstack-update-check, gstack-paths) and gstack/browse/dist/ (browse binary).
Create targeted symlinks in link.sh:
- ~/.claude/skills/gstack/bin/ → skills-external/gstack/bin/
- ~/.claude/skills/gstack/browse/dist/ → skills-external/gstack/browse/dist/
Fixes: browse binary not found, gstack-config failures, freeze gstack-paths
resolution. Safe with profile toggles (profiles move per-skill dirs, not
the gstack/ infra dir). Safe with stale link cleanup (only removes -L
symlinks, not real dirs created by mkdir -p).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
OCR/image-based PDF pipeline: convert pages to PNGs, read with Claude
Vision (bypasses unreliable OCR text layer), translate with cross-page
glossary consistency, reconstruct faithful HTML via /design-html.
5 steps: deps check → page images + assets → style analysis →
page-by-page read+translate → HTML reconstruction → visual QA.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Replace readme → doc in EXPECTED_SKILLS (readme skill was replaced by doc)
- Replace readme-updater → doc-syncer in EXPECTED_AGENTS
- Skip external/symlinked skills in disable-model-invocation check —
external skills (frontend-design, emil-design-eng, darwin-skill, find-skills)
and gstack skills (symlinked SKILL.md) are not owned by this repo
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
frontend-design (Anthropic's anti-AI-slop skill) was installed but not
referenced in the plugin-advisor decision table, recommended sets, or
conditional rules — nor in the design-gate detection logic.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Source: anthropic-agent-skills plugin cache → skills-external/frontend-design/
Auto-install via install-plugins.sh step 8b, auto-update via update-all.sh
step 7.1, symlinked by link.sh (refactored to loop over EXTERNAL_SKILLS).
Added to profiles: design, web, web-full, full.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Windows/cross-platform statusline hook for caveman mode indicator.
Reads .caveman-active flag with symlink and size guards to prevent
injection via crafted flag files.
Co-Authored-By: Claude <noreply@anthropic.com>
Major SKILL.md rewrite:
- Fast path: skip extraction when graph exists and user asks a question
- Gemini backend replaces Kimi as default external LLM
- All file I/O uses ensure_ascii=False + encoding="utf-8"
- Monorepo support via per-subfolder extraction + merge
- Obsidian/HTML export via CLI instead of inline Python
- Node ID format includes parent dir to prevent ghost duplicates
- file_type gains "concept" as valid value
- Subagent chunk paths must be absolute
- --help flag prints usage and stops
- Large corpus gate raised from 200 to 500 files
Bumps gstack submodule to 026751e.
Co-Authored-By: Claude <noreply@anthropic.com>
Query-first approach: run graphify query/path/explain for focused
questions, read GRAPH_REPORT.md only for broad architecture review.
Also fixes checkpoint→context-save routing line in CLAUDE.md.
Co-Authored-By: Claude <noreply@anthropic.com>
Session entries from two bugfix sessions:
- BLK-004: orphan /ship-feature wrapper post-refactor (resolved)
- BLK-005: profile checkpoint→context-save rename (resolved)
- BLK-006: profile.sh symlink false-negative via logical cd (resolved)
- LRN-021: sweep ~/.claude/commands/ after orchestrator migrations
- LRN-022: audit profiles against gstack skill list after submodule bump
- LRN-023: cd -P mandatory for scripts invoked via symlink
Co-Authored-By: Claude <noreply@anthropic.com>
Previously unset — Claude Code was defaulting to Opus 4.7 (1M) based on
plan capability + picker history. Pin the default to Opus 4.6 so future
sessions start on 4.6 without going through the /model picker.
1M context tier is plan-routed (Claude Max) so no explicit suffix needed
in the persisted ID — backup `.claude.json` files in this account show
the same bare form (`"model": "claude-opus-4-7"`) while runtime usage
logs as `claude-opus-4-7[1m]`.
Co-Authored-By: Claude <noreply@anthropic.com>
Drop the `PLAN` (Max/Pro) segment — user wants runtime context, not
account-tier info. Add prefixes for clarity:
- `profile: <name>` reads `<repo>/.active-profile` (already wired in
the previous commit).
- `effort: <level>` reads `.effortLevel` from `<repo>/settings.json`
via jq — picks up `/effort` changes automatically since settings.json
is the source-of-truth (symlinked into `~/.claude/settings.json`).
Sample output:
Opus 4.7 | claude (master) | profile: full | effort: xhigh | ███░░ 42% | 3m
`lib/detect-plugins.sh` is left untouched — still used by
hooks/session-start.sh, doctor.sh, update-all.sh, install-plugins.sh.
Co-Authored-By: Claude <noreply@anthropic.com>
`bash lib/profile.sh current` is 12s+ — far too slow to call from the
statusline hook (runs on every keystroke). Add a one-line cache file at
`<repo>/.active-profile`, written by `cmd_apply` and `cmd_reset`. The
statusline reads the file directly with a single `head -n1`, no
sub-shell into `profile.sh`.
Behavior:
- `bash lib/profile.sh set <name>` (which ends in `cmd_apply`) and
`bash lib/profile.sh apply <name>` both write `<name>` to
`<repo>/.active-profile`.
- `bash lib/profile.sh reset` writes the literal `none`.
- Statusline inserts the cached profile name between the plan segment
and the context-bar segment, e.g.
`Opus 4.7 | claude (master) | Max | full | ████░░░░░░ 42% | 3m`.
- Missing or empty cache → statusline shows `?`.
Cache file is gitignored — it tracks runtime state, not source.
Co-Authored-By: Claude <noreply@anthropic.com>
`lib/profile.sh:43` set `REPO="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"`.
Default `cd` preserves symlinks (logical pathname), so when the script is
invoked via the `~/.claude/lib/profile.sh` symlink, `$REPO` resolves to
`/home/bchanot-ubuntu/.claude` instead of the real repo path. `$SKILLS_DIR`
still works because `~/.claude/skills` is itself a symlink to the repo's
`skills/`. But `$DISABLED_DIR` ends up at `~/.claude/skills-disabled` (a real
sibling directory containing only stale npx-skill symlinks) while the actual
disabled gstack skills sit at `<repo>/skills-disabled`.
Symptom: `bash "$HOME/.claude/lib/profile.sh" current` returns
`none (all gstack skills enabled — no profile set)` even when a profile is
applied — because `find $DISABLED_DIR -name 'gstack__*'` returns 0.
Adding `-P` to `cd` forces physical-path resolution so `$REPO` always points
to the real repo regardless of how the script was invoked. `cmd_current`
now correctly reports `full (100% match, 14 gstack skills disabled)`.
Co-Authored-By: Claude <noreply@anthropic.com>
gstack upstream renamed the `checkpoint` skill to `context-save`
(it was shadowed by Claude Code's native /checkpoint rewind alias).
`/profile set full|dev|backend|web|web-full` was emitting
`⚠ missing: checkpoint — try: bash link.sh`, but link.sh only
materializes symlinks for skills that exist upstream — it cannot
resurrect a renamed skill, so the suggested next step was a dead
end.
Replace `checkpoint` → `context-save` in all 5 affected profiles
so the warning goes away and the new skill is enabled when the
profile is applied.
CLAUDE.md routing rule (line 193) also updated locally but left
uncommitted because the file carries an unrelated in-progress
graphify section rewrite.
Co-Authored-By: Claude <noreply@anthropic.com>
BDR-017: `full` profile = web-full + plan + dev superset for end-to-end
MVP via /init-project. Alternatives rejected: extend web-full (different
semantic), profile-of-profiles (not supported), keep 3 apply-chained.
LRN-020: sentinel/identifier collision pattern — `cmd_current`'s "full
(no profile set)" literal collided with new profile name. Renamed to
"none". Rule: sentinels must be outside the entity namespace.
Co-Authored-By: Claude <noreply@anthropic.com>
Superset of web-full + dev + audit + plan tools — covers brainstorm →
design → architecture review → scaffold → implement → ship → audit
pipeline needed by /init-project to produce a real MVP in one session.
Also renames cmd_current "no-profile" sentinel from "full" to "none"
to avoid collision with the new profile name.
Co-Authored-By: Claude <noreply@anthropic.com>
BDR-016: doc-syncer makes README AUTO+unconditional (no skip at
validation gate, only yes/edit) and DEPLOY.md prod-only with a
14-section VPS-deploy template. Mixed dev/prod DEPLOY.md flagged as
drift; dev quick-start lives only in README.
LRN-019: deployable-project doc split by audience — README = dev +
features, DEPLOY = ops + SRE. 14-section template mirrors real
VPS-deploy shape (topology, env, provisioning, two-layer firewall,
Docker tuning, persistence, backups, TLS, observability, hardening,
rollback, runbook). Drop sections that don't apply.
journal: 2026-05-15 heading covering the /commit-change run.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Toggle ui-ux-pro-max@ui-ux-pro-max-skill false → true so design-review,
design-consultation, and feat/hotfix design gate can route through it.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
README.md creation becomes AUTO and unconditional — strikes through any
"no README" opt-out in CLAUDE.md. Enriched template: Stack, Quick start
(dev), Verifying a change, Build & deploy sections, all rendered from
real project data (manifest, .env.example, scripts).
DEPLOY.md becomes prod-only, expanded into a 14-section VPS-deploy
structure (topology, env, provisioning, two-layer firewall, Docker
tuning, first-time setup, routine deploys, persistence, backups, TLS,
observability, hardening, rollback, runbook). Dev quick-start lives in
README only — mixed dev/prod DEPLOY.md is flagged as drift.
AUTO MODE: missing README surfaced as SIGNIFICANT in STEP A4 with
rendered draft for one-shot end-of-session approval. Validation gate
(STEP 8) now distinguishes AUTO patches / HUMAN items / CREATE items,
and README CREATE has no "no" — only yes/edit.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Avg score 58.0 → 78.2 across status, refactor, plugin-check,
skills-perso, commit-change. See .claude/audits/DARWIN-SKILL-2026-05-12.md.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
