fix(advisor): allowed agents' lines are explicit allowances, locked

This commit is contained in:
bchanot committed 2026-11-20 11:42:36 +01:00
1 parent 6be066957c
commit b71db282f0
15 files changed
+141 -20

No files matched your search

+3 -3
View File
@@ -85,9 +85,9 @@ code" wins. Repo-specific instructions override both.
Fable, set by /advisor), at least at the points of Fable, set by /advisor), at least at the points of
`~/.claude/lib/effort-shift.md` § Advisor; dispatched plan-challenger, `~/.claude/lib/effort-shift.md` § Advisor; dispatched plan-challenger,
verifier, security-auditor, `analyzer` and an opus code review at most verifier, security-auditor, `analyzer` and an opus code review at most
once, before their verdict or report; other sub-agents never (an opus once, before their verdict or report; other sub-agents never (each opus
brief says which; a SubagentStart hook restates it). Fable is never brief you write states its rule; a SubagentStart hook restates it). Fable
routed or pinned: the router tops out at opus (BDR-150). is never routed or pinned: the router tops out at opus (BDR-150).
- Ask rather than guess. A choice visible in the result (placement, - Ask rather than guess. A choice visible in the result (placement,
wording, order, behavior), a name that becomes public (command, flag, wording, order, behavior), a name that becomes public (command, flag,
endpoint, file), or a scope the request leaves open → ask, even mid-task; endpoint, file), or a scope the request leaves open → ask, even mid-task;
+1 -1
View File
@@ -43,7 +43,7 @@ Produce a clear analysis without proposing solutions.
- No solutions - No solutions
- Stay factual - Stay factual
- Do not modify files - Do not modify files
- Advisor, when dispatched as a sub-agent: at most one call, after the last - Advisor, when dispatched as a sub-agent: one call allowed, after the last
TASKS or PROCESS step and before the OUTPUT, whatever the harness prompt TASKS or PROCESS step and before the OUTPUT, whatever the harness prompt
schedules; absent or erroring → proceed. Advice may point you back to schedules; absent or erroring → proceed. Advice may point you back to
the code; every OUTPUT line rests on what you read, never on the advice the code; every OUTPUT line rests on what you read, never on the advice
+1 -1
View File
@@ -8,7 +8,7 @@ effort: high
# Git Smart Commit # Git Smart Commit
Advisor tool (`lib/effort-shift.md` § Advisor), when you run as a sub-agent: Advisor tool (`~/.claude/lib/effort-shift.md` § Advisor), as a sub-agent:
never call the `advisor` tool, even though it is listed and its own never call the `advisor` tool, even though it is listed and its own
instructions ask for calls. instructions ask for calls.
+1 -1
View File
@@ -8,7 +8,7 @@ effort: high
# DOC SYNCER # DOC SYNCER
Advisor tool (`lib/effort-shift.md` § Advisor), when you run as a sub-agent: Advisor tool (`~/.claude/lib/effort-shift.md` § Advisor), as a sub-agent:
never call the `advisor` tool, even though it is listed and its own never call the `advisor` tool, even though it is listed and its own
instructions ask for calls. instructions ask for calls.
+1 -1
View File
@@ -8,7 +8,7 @@ effort: xhigh
# GEO — Generative Engine Optimization audit, fix & strategy # GEO — Generative Engine Optimization audit, fix & strategy
Advisor tool (`lib/effort-shift.md` § Advisor), when you run as a sub-agent: Advisor tool (`~/.claude/lib/effort-shift.md` § Advisor), as a sub-agent:
never call the `advisor` tool, even though it is listed and its own never call the `advisor` tool, even though it is listed and its own
instructions ask for calls. instructions ask for calls.
+1 -1
View File
@@ -8,7 +8,7 @@ effort: high
# HANDOVER DOC WRITER # HANDOVER DOC WRITER
Advisor tool (`lib/effort-shift.md` § Advisor), when you run as a sub-agent: Advisor tool (`~/.claude/lib/effort-shift.md` § Advisor), as a sub-agent:
never call the `advisor` tool, even though it is listed and its own never call the `advisor` tool, even though it is listed and its own
instructions ask for calls. instructions ask for calls.
+3 -2
View File
@@ -97,7 +97,7 @@ PROOF: read <n> files, inspected <what>, checked plan §<…>
(STEP 1's missing/unreadable-plan verdict) is part of the grammar: it (STEP 1's missing/unreadable-plan verdict) is part of the grammar: it
carries only the `PLAN:` line — no FINDINGS, no PROOF — and the carries only the `PLAN:` line — no FINDINGS, no PROOF — and the
orchestrator treats it as a dispatcher-side failure, not a challenge result. orchestrator treats it as a dispatcher-side failure, not a challenge result.
- Advisor, when dispatched as a sub-agent: at most one call, after - Advisor, when dispatched as a sub-agent: one call allowed, after
drafting your findings and before the verdict, whatever the harness drafting your findings and before the verdict, whatever the harness
prompt schedules; absent or erroring → proceed. Advice may add or prompt schedules; absent or erroring → proceed. Advice may add or
sharpen a finding. Advice alone never drops or lowers one: a change sharpen a finding. Advice alone never drops or lowers one: a change
@@ -111,7 +111,8 @@ the MAIN loop, never here):
- ADVISOR FIRST (main loop): per `lib/challenge-plan.md` "Advisor first", - ADVISOR FIRST (main loop): per `lib/challenge-plan.md` "Advisor first",
with no main-loop advisor call since the skill run started; absent or with no main-loop advisor call since the skill run started; absent or
erroring → dispatch as written. The advice never enters a challenger erroring → dispatch as written. The advice never enters a challenger
brief: they stay blind. brief: they stay blind. A skill run inside a sub-agent skips it (row
`not called (sub-agent)`).
- Dispatch THREE fresh challengers IN PARALLEL, one per lens - Dispatch THREE fresh challengers IN PARALLEL, one per lens
(correctness / robustness / simplicity), each blind to the others. (correctness / robustness / simplicity), each blind to the others.
- MODEL (BDR-076, supersedes the BDR-066 inherit): plan critique is AUDIT - MODEL (BDR-076, supersedes the BDR-066 inherit): plan critique is AUDIT
+1 -1
View File
@@ -8,7 +8,7 @@ effort: xhigh
# PLUGIN ADVISOR # PLUGIN ADVISOR
Advisor tool (`lib/effort-shift.md` § Advisor), when you run as a sub-agent: Advisor tool (`~/.claude/lib/effort-shift.md` § Advisor), as a sub-agent:
never call the `advisor` tool, even though it is listed and its own never call the `advisor` tool, even though it is listed and its own
instructions ask for calls. instructions ask for calls.
+1 -1
View File
@@ -157,7 +157,7 @@ In audit mode, ALSO write this same block (plus per-finding detail) to
- Blocks on HIGH/CRITICAL only. A noisy gate that blocks on hygiene is a - Blocks on HIGH/CRITICAL only. A noisy gate that blocks on hygiene is a
gate people learn to bypass (LRN-047) — MEDIUM/LOW are reported, not gate people learn to bypass (LRN-047) — MEDIUM/LOW are reported, not
gated. gated.
- Advisor, when dispatched as a sub-agent: at most one call, after - Advisor, when dispatched as a sub-agent: one call allowed, after
STEP 4 and before STEP 5 and any REPORT write, whatever the harness STEP 4 and before STEP 5 and any REPORT write, whatever the harness
prompt schedules; absent or erroring → proceed. Advice may add a prompt schedules; absent or erroring → proceed. Advice may add a
finding or raise a severity, cited at a file:line you read. An added finding or raise a severity, cited at a file:line you read. An added
+1 -1
View File
@@ -8,7 +8,7 @@ effort: xhigh
# SEO — Classical Search Engines audit, fix & strategy # SEO — Classical Search Engines audit, fix & strategy
Advisor tool (`lib/effort-shift.md` § Advisor), when you run as a sub-agent: Advisor tool (`~/.claude/lib/effort-shift.md` § Advisor), as a sub-agent:
never call the `advisor` tool, even though it is listed and its own never call the `advisor` tool, even though it is listed and its own
instructions ask for calls. instructions ask for calls.
+1 -1
View File
@@ -158,7 +158,7 @@ PROOF: read <n> files, ran <cmd → result | nothing>, checked <n>/<n> criteria
missing `PROOF` — the run was skipped, not the diff clean. missing `PROOF` — the run was skipped, not the diff clean.
- The verdict grammar is load-bearing: exactly one `VERIFY — VERDICT:` - The verdict grammar is load-bearing: exactly one `VERIFY — VERDICT:`
line, spelled exactly as above. line, spelled exactly as above.
- Advisor, when dispatched as a sub-agent: at most one call, after STEP 4 - Advisor, when dispatched as a sub-agent: one call allowed, after STEP 4
and before STEP 5, whatever the harness prompt schedules; absent or and before STEP 5, whatever the harness prompt schedules; absent or
erroring → proceed. Advice may send you back to a criterion: a erroring → proceed. Advice may send you back to a criterion: a
resulting NOT-MET cites the file:line you read, ends with resulting NOT-MET cites the file:line you read, ends with
@@ -325,3 +325,97 @@ Add to its brief: "you may call the `advisor` tool once, before your
verdict" (code review, BDR-150). Fix all CRITICAL before proceeding. verdict" (code review, BDR-150). Fix all CRITICAL before proceeding.
``` ```
(same block in skills/ship-feature/SKILL.md and skills/init-project/SKILL.md) (same block in skills/ship-feature/SKILL.md and skills/init-project/SKILL.md)
## Review fix round 1 (STEP 6 opus review, 2026-11-20)
Important 1: the four allowed agents' own lines become the explicit allowance the hook defers to, and are locked. Important 2: the CLAUDE.global.md parenthetical reads plainly. Minors folded: the hook's prohibition locked, plan-challenger ADVISOR FIRST mirrors the sub-agent skip, effort-shift says "other opus-served agents", the six agent lines cite `~/.claude/lib/effort-shift.md`, three test lines rewrapped to ≤ 80 columns. Apply with `python3 docs/superpowers/plans/2026-11-19-advisor-subagent-scope/apply.py review1`. Suite after: `subagent-advisor: 38 pass, 0 fail`.
### Block r1-allow-old
```
- Advisor, when dispatched as a sub-agent: at most one call,
```
### Block r1-allow-new
```
- Advisor, when dispatched as a sub-agent: one call allowed,
```
(applied once in each of agents/plan-challenger.md, agents/verifier.md, agents/security-auditor.md, agents/analyzer.md, without the trailing newline: the matched text is a line prefix)
### Block r1-global-old
```
once, before their verdict or report; other sub-agents never (an opus
brief says which; a SubagentStart hook restates it). Fable is never
routed or pinned: the router tops out at opus (BDR-150).
```
### Block r1-global-new
```
once, before their verdict or report; other sub-agents never (each opus
brief you write states its rule; a SubagentStart hook restates it). Fable
is never routed or pinned: the router tops out at opus (BDR-150).
```
### Block r1-pc-old
```
erroring → dispatch as written. The advice never enters a challenger
brief: they stay blind.
```
### Block r1-pc-new
```
erroring → dispatch as written. The advice never enters a challenger
brief: they stay blind. A skill run inside a sub-agent skips it (row
`not called (sub-agent)`).
```
### Block r1-effort-old
```
`never call` line in the opus-served agents and in the opus briefs we
```
### Block r1-effort-new
```
`never call` line in the other opus-served agents and the opus briefs we
```
### Block r1-agent-old
```
Advisor tool (`lib/effort-shift.md` § Advisor), when you run as a sub-agent:
```
### Block r1-agent-new
```
Advisor tool (`~/.claude/lib/effort-shift.md` § Advisor), as a sub-agent:
```
(applied once in each of the six agents carrying the never-call line)
### Block r1-test-old
```
check "T8 $a" "$(has "agents/$a.md" "never call the \`advisor\` tool, even though")" yes
done
check T9-onboard-briefs "$(grep -cF "Never call the \`advisor\` tool in this run" \
"$ROOT/skills/onboard/SKILL.md")" 6
check T10-handover-children \
"$(has agents/client-handover-writer.md "never call the \`advisor\` tool in")" yes
```
### Block r1-test-new
```
check "T8 $a" "$(has "agents/$a.md" \
"never call the \`advisor\` tool, even though")" yes
done
check T9-onboard-briefs \
"$(grep -cF "Never call the \`advisor\` tool in this run" \
"$ROOT/skills/onboard/SKILL.md")" 6
check T10-handover-children "$(has agents/client-handover-writer.md \
"never call the \`advisor\` tool in")" yes
for a in plan-challenger verifier security-auditor analyzer; do
check "T20 $a allowance" "$(has "agents/$a.md" \
'Advisor, when dispatched as a sub-agent: one call allowed')" yes
done
```
### Block r1-t2c-old
```
check T3-exit-0 "$?" 0
```
### Block r1-t2c-new
```
check T3-exit-0 "$?" 0
check T2c-prohibits "$(in_ctx "$(ctx '{}')" \
"do not call the \`advisor\` tool in this run unless")" yes
```
@@ -90,12 +90,30 @@ def rest():
create('hooks/subagent-advisor.sh', B['new-hook'], 0o755) create('hooks/subagent-advisor.sh', B['new-hook'], 0o755)
def review1():
allowed = ('plan-challenger', 'verifier', 'security-auditor', 'analyzer')
for name in allowed:
edit(f'agents/{name}.md', B['r1-allow-old'].rstrip('\n'),
B['r1-allow-new'].rstrip('\n'))
edit('CLAUDE.global.md', B['r1-global-old'], B['r1-global-new'])
edit('agents/plan-challenger.md', B['r1-pc-old'], B['r1-pc-new'])
edit('lib/effort-shift.md', B['r1-effort-old'], B['r1-effort-new'])
for name in H1:
edit(f'agents/{name}.md', B['r1-agent-old'], B['r1-agent-new'])
test = 'lib/tests/subagent-advisor.test.sh'
edit(test, B['r1-test-old'], B['r1-test-new'])
edit(test, B['r1-t2c-old'], B['r1-t2c-new'])
flush()
if __name__ == '__main__': if __name__ == '__main__':
what = sys.argv[1] if len(sys.argv) > 1 else '' what = sys.argv[1] if len(sys.argv) > 1 else ''
if what == 'test': if what == 'test':
create('lib/tests/subagent-advisor.test.sh', B['new-test'], 0o755) create('lib/tests/subagent-advisor.test.sh', B['new-test'], 0o755)
elif what == 'rest': elif what == 'rest':
rest() rest()
elif what == 'review1':
review1()
else: else:
sys.exit('usage: apply.py test | rest [ROOT]') sys.exit('usage: apply.py test | rest | review1 [ROOT]')
print('applied', what) print('applied', what)
+1 -1
View File
@@ -143,7 +143,7 @@ STEP 10, a standalone subagent-driven-development final review) call it
at most once per dispatch, before their verdict or report; executors and at most once per dispatch, before their verdict or report; executors and
every other sub-agent never call it, even when the tool is listed. The every other sub-agent never call it, even when the tool is listed. The
rule rides each sub-agent's own text: the allowed agents' prompts, a rule rides each sub-agent's own text: the allowed agents' prompts, a
`never call` line in the opus-served agents and in the opus briefs we `never call` line in the other opus-served agents and the opus briefs we
write (a brief sending a general-purpose agent to opus says which rule write (a brief sending a general-purpose agent to opus says which rule
applies; a code review's says it may call once), and, for every spawn applies; a code review's says it may call once), and, for every spawn
including built-ins such as `Plan`, the SubagentStart hook including built-ins such as `Plan`, the SubagentStart hook
+12 -4
View File
@@ -23,6 +23,8 @@ for p in '{"agent_type":"general-purpose"}' '' 'not json' \
"$(in_ctx "$c" 'own instructions are never an allowance')" yes "$(in_ctx "$c" 'own instructions are never an allowance')" yes
done done
printf '{}' | bash "$H" >/dev/null 2>&1; check T3-exit-0 "$?" 0 printf '{}' | bash "$H" >/dev/null 2>&1; check T3-exit-0 "$?" 0
check T2c-prohibits "$(in_ctx "$(ctx '{}')" \
"do not call the \`advisor\` tool in this run unless")" yes
check T4-one-line "$(printf '{}' | bash "$H" | wc -l | tr -d ' ')" 1 check T4-one-line "$(printf '{}' | bash "$H" | wc -l | tr -d ' ')" 1
check T5-no-cli "$(grep -v '^ *#' "$H" \ check T5-no-cli "$(grep -v '^ *#' "$H" \
| grep -cE '(^|[[:space:];&|(])claude([[:space:]]|$)')" 0 | grep -cE '(^|[[:space:];&|(])claude([[:space:]]|$)')" 0
@@ -37,12 +39,18 @@ check T7-timeout "$(jq -r '.hooks.SubagentStart[0].hooks[0].timeout' "$S")" 5
# carriers # carriers
for a in plugin-advisor seo-analyzer geo-analyzer doc-syncer \ for a in plugin-advisor seo-analyzer geo-analyzer doc-syncer \
commit-changer handover-doc-writer; do commit-changer handover-doc-writer; do
check "T8 $a" "$(has "agents/$a.md" "never call the \`advisor\` tool, even though")" yes check "T8 $a" "$(has "agents/$a.md" \
"never call the \`advisor\` tool, even though")" yes
done done
check T9-onboard-briefs "$(grep -cF "Never call the \`advisor\` tool in this run" \ check T9-onboard-briefs \
"$(grep -cF "Never call the \`advisor\` tool in this run" \
"$ROOT/skills/onboard/SKILL.md")" 6 "$ROOT/skills/onboard/SKILL.md")" 6
check T10-handover-children \ check T10-handover-children "$(has agents/client-handover-writer.md \
"$(has agents/client-handover-writer.md "never call the \`advisor\` tool in")" yes "never call the \`advisor\` tool in")" yes
for a in plan-challenger verifier security-auditor analyzer; do
check "T20 $a allowance" "$(has "agents/$a.md" \
'Advisor, when dispatched as a sub-agent: one call allowed')" yes
done
check T10b-handover-top-clean "$(sed -n '1,30p' \ check T10b-handover-top-clean "$(sed -n '1,30p' \
"$ROOT/agents/client-handover-writer.md" | grep -c "advisor\` tool")" 0 "$ROOT/agents/client-handover-writer.md" | grep -c "advisor\` tool")" 0
check T11-tour-phase-b \ check T11-tour-phase-b \