Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add xdg/xdg-claude --skill decision-loggit clone --depth 1 https://github.com/xdg/xdg-claudeWrote 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/xdg/xdg-claude/decision-log)<a href="https://agentmods.dev/skills/xdg/xdg-claude/decision-log"><img src="https://agentmods.dev/badge/skills/xdg/xdg-claude/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/xdg/xdg-claude/decision-log"><img src="https://agentmods.dev/badge/skills/xdg/xdg-claude/decision-log.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 38 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00083 | $0.01071 |
| Opus 5.5 | $0.00033 | $0.00428 |
| Sonnet 5.5 | $0.00017 | $0.00214 |
| Haiku 4.5 | $0.00008 | $0.00107 |
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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision log
An append-only log of choices that constrain future work: what was decided, when, and why the alternatives lost. It exists so a future reader -- the user, a contributor, or a later session -- does not relitigate a settled question or silently undo it.
When to log a decision
Log a decision when all of these hold:
- Real alternatives existed and one was chosen.
- The choice constrains future work, or a future reader would otherwise be tempted to change it back.
- The reasoning is not recoverable from the diff alone.
Typical: dependency and version pins, protocol/interface choices, deployment topology, deliberate omissions ("no X, because the pinned version cannot"), security trade-offs, and reversals of earlier entries.
Not log-worthy: refactors, renames, formatting, bug fixes, anything the code plus a commit message already explains. A log padded with trivia stops being read.
Where the log lives
- If the project's
CLAUDE.md(orAGENTS.md) names a decision-log path, use it. - Otherwise
docs/decisions.md. - If that is absent, check for
DECISIONS.md,doc/decisions.md, or anadr//docs/adr/directory before concluding there is none.
Before writing, verify the ground
Never create a decision log, and never restructure an existing one, without asking the user first. Many repos -- especially ones the user does not own -- have their own conventions or want none of this.
- Log exists and follows the template below -- append. No need to ask.
- Log exists but uses a different format (ADR-per-file, a table, numbered records) -- follow that repo's format. Match its headings, numbering, and field names. Do not convert it to this template.
- Log exists and is formatted ambiguously -- show the user one existing entry and ask whether to match it or use this skill's template.
- No log anywhere -- stop and ask: "This repo has no decision log. Start one
at
<path>?" Take no action on a refusal, and do not re-ask in that session.
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.
- 1mo ago Changed 5f2e2a00b021
- 2mo ago First seen · 105 lines · 83 tokens per session scan A 34a4e66626bc
decision-log is a skill published in the GitHub repository xdg/xdg-claude (20 stars, last pushed 6d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,071 once invoked, about $0.0003 per session on Opus 5.5. 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.
decision-log compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| decision-logxdg/xdg-claude | Skill | 20 | 6d ago | Apache-2.0 | A | 83 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |