Borrowing it
Nothing to install: this file belongs to asdecided/core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/asdecided/core/main/.claude/skills/decided-review/SKILL.mdgit clone --depth 1 https://github.com/asdecided/coreWrote 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/asdecided/core/decided-review)<a href="https://agentmods.dev/skills/asdecided/core/decided-review"><img src="https://agentmods.dev/badge/skills/asdecided/core/decided-review/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/asdecided/core/decided-review"><img src="https://agentmods.dev/badge/skills/asdecided/core/decided-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.00835 |
| Opus 5.5 | $0.00024 | $0.00334 |
| Sonnet 5.5 | $0.00012 | $0.00167 |
| Haiku 4.5 | $0.00006 | $0.00084 |
Grade A, and why
decided-review 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 2mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AsDecided corpus review
decided review <dir> validates every artifact, checks every relationship, and
reports findings grouped by priority, worst first. This skill is the
procedure for working that report down: blocking findings first, then
advisory ones, re-validating after each fix.
Hard constraints
- Write artifact files only inside the host project's decisions directory
(
decisions/by default; if the project keeps artifacts elsewhere, confirm the path before writing). Never create or edit RAC artifacts outside that directory, and never modify files elsewhere in the project on this skill's behalf. - Never hand-write or alter an artifact
idor its frontmatter identity block. Do not edit.decisions/config.yaml. - Do not invent sections or frontmatter fields. Use
decided schema <type>to see what a type expects. - The work is done only when
decided validate <dir>anddecided relationships <dir> --validateboth exit 0.
Run the review
decided review <dir> # findings grouped by priority, worst first
decided review <dir> --json # stable contract for scripted triage
Exit 1 means blocking findings exist; exit 0 with findings means only advisory items remain. Findings are grouped by priority:
- Invalid artifacts — validation errors (blocking)
- Broken relationships — unresolvable references (blocking)
- Unrecognized artifacts — no schema matched (advisory)
- Missing recommended information (advisory)
Work strictly in priority order. Each finding carries a suggested action; start from it.
Mechanical findings — missing sections
Missing recommended sections are mechanical: the fix is adding the section with real content.
decided improve <file> # missing sections, with guidance prompts
decided improve <file> --template # Markdown stubs for the missing sections
Paste the stub, then replace its placeholder text with real content. Do not add a section purely to silence a finding — when no real content exists, an advisory finding may stand.
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.
- 2mo ago First seen · 95 lines · 59 tokens per session scan A fb86ffbf6844
decided-review is a skill published in the GitHub repository asdecided/core (300 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 835 once invoked, about $0.0002 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.
Other skills, from other repositories
crit-cli
Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file.…
crit
Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
review
Adversarial review of an increment before it ships, by a fresh context or another model family; every finding cites path:line and is re-verified. Use for "review", "qa", "critique this".
sw-review
Adversarial review of an increment before it ships, by a fresh context or another model family; every finding cites path:line and is re-verified. Use for "review", "qa", "critique this".
format-markdown
Formats Markdown files consistently using project-native tooling first (repo scripts/config), then safe fallback formatters, and verifies the result with lint/check commands. Invoked when the user asks to format markdown, tidy docs, normalize README files, or fix markdown style drift.