Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kimsanguine/hplannpx agentmods add skills/kimsanguine/hplan/decision-logWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kimsanguine/hplan/decision-log)<a href="https://agentmods.dev/skills/kimsanguine/hplan/decision-log"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/decision-log.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.01243 |
| Opus 5 | $0.00044 | $0.00622 |
| Sonnet 5 | $0.00018 | $0.00249 |
| Haiku 4.5 | $0.00009 | $0.00124 |
Grade A, and why
decision-log scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Log — Self-Calibrating Build Gate
Running for: $ARGUMENTS
Core Goal
- 모든 gate 결정을
harness/decisions.jsonl에 append-only로 기록 → 3-6개월 뒤 audit으로 hit_rate 측정. - false_hold (hold 했는데 외부에서 성공함) + missed_build (build 했는데 죽음)을 자동 추출 → rubric 보정 데이터.
- "내 게이트가 정확한가?"라는 질문에 답할 수 있는 유일한 PM skill.
Trigger Gate
Use This Skill When
- 매 build/interview/pivot/hold/CONDITIONAL_GO 결정 시 즉시 호출 (의무)
- 3-6개월 뒤 outcome이 확정됐을 때 backfill
- 분기별 self-review — "지난 분기 결정 중 정확했던 비율은?"
Route to Other Skills When
- audit 결과 false_hold 다수 →
evidence-rubric의 threshold 검토 - missed_build 다수 → Evidence Gate 통과 기준 강화
- decision =
hold+ 영구 사유 →exclusionsadd 같이 호출 - decision =
build→handoff로 라우팅
Boundary Checks
- ❌ 영구 삭제 불가 (append-only). 잘못된 entry는 새 entry로 supersede.
- ❌ outcome backfill 없으면 audit이 의미 없음 — 잊지 말 것.
- ❌
--from-hitl은 이미 기록된 HITL id만 허용. 없는 id를 주면 거부된다 (끊어진 승격 링크 방지). - ⚠️
--root는harness/자체가 아니라 그 부모 디렉터리를 가리킨다.
Inputs
# Log a decision
python3 hplan/scripts/decision_log.py log \
--project alpha-app --gate build --decision build --score 78 \
--reason "5/5 강한 신호" --reason "COGS GREEN"
# Promote an earlier HITL decision into a gate decision
python3 hplan/scripts/decision_log.py log \
--project alpha-app --gate build --decision build --score 78 \
--from-hitl hitl-2026-07-28-ab12c
# Backfill outcome (3-6 months later)
python3 hplan/scripts/decision_log.py update --id dec-XXX --outcome shipped
# Audit — single project
python3 hplan/scripts/decision_log.py audit
# Audit — aggregate calibration across several projects
python3 hplan/scripts/decision_log.py audit --root ../alpha --root ../beta
Steps
- 결정이 내려진 직후
log호출 (--reason다중 사용 권장). - project name + gate (evidence/product/build) + decision 명시.
- 매주/매월
audit호출 — pending decisions 확인. - outcome이 확정되면 즉시
update --id <id> --outcome <state>. - 분기별 audit으로 hit_rate trend 점검.
Outputs
harness/decisions.jsonl(append-only)- audit returns:
total, resolved, pending, by_decision, by_decision_outcome, hit_rate, false_holds, missed_builds, guidance
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 110 lines · 88 tokens per session scan A e468327b474e
decision-log is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 22d ago), licensed MIT. It adds 88 tokens to every session and 1,243 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…
recap-doc
Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…
runbook
Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.