OpenHarness Bot
8a12562b05
Second-round council (5 critics × distinct lenses: faithfulness,
codebase-fit, practical-usability, safety, editor) surfaced findings
the original 3-critic pass missed. Applying.
HIGH-severity fixes:
- Faithfulness disclaimer: RAO is an RL training paper; its
quantitative gains (depth-12 generalization, 2.5x wall-clock,
context-overflow handling) require a trained policy this harness
does not have. The rule now opens with this disclaimer and
explicitly notes Max depth / Step budget are prompt-level
conventions, not runtime caps.
- launch_subagent vs Agent tool: paper's async REPL primitive runs
asyncio coroutines with shared state. Harness Agent tool is
stateless and synchronous. Rule now distinguishes them in
§ Multi-Level Delegation Protocol.
- Enforcement gate added: .claude/skills/delegate/SKILL.md Step 5
gains sub-step a.1 — before spawning a worker authorized to
recurse, confirm Max depth / Max children per level / Step budget
are ALL present. Missing → flat execution only.
- .claude/protected-paths.txt: new rule registered as load-bearing
(now cross-referenced from advisor-model.md and delegate SKILL).
MEDIUM-severity fixes:
- Branching-factor cap added: Max children per level: 5 (hard cap)
alongside Max depth, closing the depth-4 * parallel-spawn fanout
risk.
- Internal duplication cut: dropped "Recursion as Context
Expansion" section (already covered by When-to-Use triggers
+ Recursing-for-reasoning anti-pattern); dropped tautological
Step 4 in protocol; dropped duplicated "no raw content in Goal"
rule; dropped Orchestrator Boundary second paragraph;
dropped See Also entry for repo-layout-source.md (no referent
in this file).
- Ambiguous "Step 5" cross-ref tightened to
"§ 5 Execute waves sub-step (a)".
- "context capacity" trigger reframed to "child's briefing would
exceed one sub-agent's effective context window" — concrete
enough to act on.
- New anti-pattern: "Synthesis pass-through" — mid-tree node
forwards children's outputs verbatim, adds zero value.
- New anti-pattern: "Sideways scope escalation" — child rewriting
a sibling's briefing to lift depth/scope.
Net file size: 121 -> 114 lines. New content (disclaimers,
branching cap, new anti-patterns) more than offset by cuts of
duplicated and tautological text. CHANGELOG entry updated to
reflect the disclaimers and the new enforcement gate.
Closes #269 (continuing).
65 lines
1.8 KiB
Plaintext
65 lines
1.8 KiB
Plaintext
# Protected paths — load-bearing skills, scripts, and config that critics
|
|
# must NOT propose for deletion or deprecation without an explicit override
|
|
# note in the finding's RECOMMENDATION column.
|
|
#
|
|
# When you ship a new orchestrator-load-bearing skill or script, ADD it
|
|
# here in the same PR. When something on this list becomes truly obsolete,
|
|
# remove it here in a separate PR with a CHANGELOG entry explaining why.
|
|
#
|
|
# Format: one entry per line. Skill names are bare (e.g., "release"), not
|
|
# slash-prefixed. Scripts and files use repo-relative paths.
|
|
# Lines starting with # are comments. Blank lines are ignored.
|
|
#
|
|
# Last reviewed: 2026-05-03 (issue #218)
|
|
|
|
# --- Orchestrator skills (.claude/skills/) ---
|
|
release
|
|
ci-status
|
|
cloudflared-tunnel
|
|
agent-browser
|
|
prd
|
|
ralph
|
|
harness-audit
|
|
skill-lint
|
|
delegate
|
|
strategic-proposal
|
|
ship-spec
|
|
|
|
# --- Orchestrator scripts (scripts/) ---
|
|
scripts/ralph.sh
|
|
scripts/cron-runtime.ts
|
|
|
|
# --- Root lifecycle entrypoints ---
|
|
Makefile
|
|
|
|
# --- Install / runtime scripts wired into the Dockerfile or sourced at boot ---
|
|
install/banner.sh
|
|
install/cloudflared-tunnel.sh
|
|
.devcontainer/entrypoint.sh
|
|
.devcontainer/Dockerfile
|
|
|
|
# --- Crons (referenced by scripts/cron-runtime.ts) ---
|
|
crons/heartbeat.md
|
|
crons/cleanup-tasks.md
|
|
|
|
# --- Rules consumed by skills + agents at runtime ---
|
|
.claude/rules/git.md
|
|
.claude/rules/sandbox-processes.md
|
|
.claude/rules/advisor-model.md
|
|
.claude/rules/recursive-delegation.md
|
|
|
|
# --- Specs that other artifacts cross-reference ---
|
|
.claude/specs/structure-spec-v0.7.md
|
|
.claude/ICP.md
|
|
|
|
# --- Orchestrator identity layer (session-loaded by AGENTS.md bootloader) ---
|
|
context/SOUL.md
|
|
context/IDENTITY.md
|
|
context/TOOLS.md
|
|
context/USER.md
|
|
|
|
# --- Sub-agents invoked by skills ---
|
|
.claude/agents/critic.md
|
|
.claude/agents/implementer.md
|
|
.claude/agents/pm.md
|