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/moonlight-lupin/agent-skillsnpx agentmods add skills/moonlight-lupin/agent-skills/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/moonlight-lupin/agent-skills/decision-log)<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/decision-log"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/decision-log/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/decision-log"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/decision-log.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 306 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
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 | $0.00039 | $0.02508 |
| Opus 5 | $0.00019 | $0.01254 |
| Sonnet 5 | $0.00008 | $0.00502 |
| Haiku 4.5 | $0.00004 | $0.00251 |
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 10d 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Log
Overview
Use this skill to keep durable, searchable decision records when a team or agent needs to remember what was decided, why it was decided, what alternatives were considered, and when the decision should be reviewed.
It solves recurring problems that chat history and meeting notes do not solve well:
- Decisions get buried in long conversations and are hard to find later.
- The reasoning and constraints behind a choice are forgotten.
- Settled questions get re-litigated because there is no authoritative record.
- Reversals are made by deleting old context instead of preserving history.
- No review cadence exists, so time-sensitive decisions quietly go stale.
The pattern is ADR-style: one Markdown file per decision, numbered sequentially, with status, context, options, decision, consequences, and review metadata. The format follows the spirit of Michael Nygard's Architecture Decision Record (ADR) pattern, generalized for product, operations, research, and team decisions.
Decision records live in a configurable directory:
--decisions-dir DIRon every command, orDECISIONS_DIR=/path/to/decisions, or- default
./decisions/relative to the current working directory.
Quick start
python scripts/decision_log.py new --title "Use SQLite for source-tracker"
The command creates the next numbered file, such as:
./decisions/ADR-001-use-sqlite-for-source-tracker.md
Open the printed path, complete the sections, then change ## Status from
proposed to accepted once the decision is approved.
When to create an ADR
Create a decision record when the choice is meaningful enough that future people will ask "why did we do this?" Examples:
- Architecture, storage, API, dependency, deployment, or security choices.
- Product or workflow choices that affect multiple users or future work.
- Trade-offs with real costs, constraints, or excluded alternatives.
- Decisions that may need review after a date, milestone, or external trigger.
- Reversals of previous decisions.
What ships with it
6 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.
- 10d ago First seen · 342 lines · 39 tokens per session scan A f45bd4374ea4
decision-log is a skill published in the GitHub repository moonlight-lupin/agent-skills (60 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 2,508 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
mnemosyne-maintenance
Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.
status
Use when the user wants a one-screen view of current hyperflow project state — version, profile freshness, memory count, and live progress on every in-flight task. Read-only; never modifies state, never dispatches workers. Trigger with /hyperflow:status, "what is hyperflow doing", "show task progress", "where are we".
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
exploiting-format-string-vulnerabilities
Methodology for exploiting format string bugs where attacker-controlled data reaches the format argument of printf-family functions, enabling stack/memory disclosure (info leaks for ASLR/PIE/canary defeat) and arbitrary write primitives (%n) to hijack control flow via GOT/.finiarray overwrites.
taiyi-compress
A workflow tool for shrinking large coding-agent conversations and work files into shorter context notes. It can also coordinate separate agents for parallel development and create handoff notes for continuing work in a new session.