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-capture/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-capture)<a href="https://agentmods.dev/skills/asdecided/core/decided-capture"><img src="https://agentmods.dev/badge/skills/asdecided/core/decided-capture/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-capture"><img src="https://agentmods.dev/badge/skills/asdecided/core/decided-capture.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 | $0.00113 | $0.01861 |
| Opus 5.5 | $0.00045 | $0.00744 |
| Sonnet 5.5 | $0.00023 | $0.00372 |
| Haiku 4.5 | $0.00011 | $0.00186 |
Grade A, and why
decided-capture 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAC interview capture
Turn a conversation into one valid RAC artifact. You interview the author and
propose; the human ratifies; decided validate is the deterministic check; an
independent reviewer promotes it by pull request. This skill never adds AI to the
AsDecided core — it runs in the coding agent and uses the decided CLI.
Hard constraints
- Capture knowledge, not work. Record a decision or a long-lived requirement and its rationale — never owners, assignees, sprints, priorities, or due dates. If the conversation is about who does what by when, that belongs in the team's work tracker, not in RAC; say so and stop.
- The schema is not yours to invent. Read the real shape with
decided schema <type>(anddecided schemafor the recognised types). Use the real section names, the real artifact types, and the real## Related <Type>relationship sections. Never guess or hard-code a field, type, or relationship kind. If you cannot rundecided schema, stop and say so. - No invention. Capture only what the author actually tells you. Where a required section has no material, ask a question — do not fill it with plausible-sounding text. The interview gathers facts; it does not author them.
- Human ratification is mandatory and explicit (before any file is written).
Present the draft and require the user to confirm or correct (a) the artifact
type, (b) the title, and (c) each relationship before you write anything.
Relationships are suggestions to confirm, never silently asserted. The
idis minted bydecided new(opaque, system-assigned) — never hand-write or choose it. - Close on deterministic validation. After writing, run
decided validate. If it fails, show the errors, offer to fix them, and re-validate. Never leave an invalid artifact behind. - Save is a draft commit; promotion is a pull request. A fresh capture is untrusted until a human reviews it. Write the artifact, optionally commit it as a draft on a branch when the user confirms, but never write straight to the trusted corpus, never auto-commit without confirmation, and never self-merge. The trust boundary is review and merge by someone other than the author.
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 · 164 lines · 113 tokens per session scan A 9582d612e8fe
decided-capture is a skill published in the GitHub repository asdecided/core (300 stars, last pushed yesterday), licensed Apache-2.0. It adds 113 tokens to every session and 1,861 once invoked, about $0.0005 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
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.
project-docs
Software development project documentation management and progress tracking. Use when: (1) Initializing a new software project and need to create all required documentation (MRD, PRD, Technical Plan, Roadmap), (2) Updating project roadmap after completing tasks, (3) Getting a summary of current project progress, (4)…
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.
processing-markdown
Processes Markdown files using mq, a jq-like query language for Markdown. Use when the user mentions Markdown processing, content extraction, document transformation, or mq queries.
web-scraping
Fetches web pages and extracts structured data using mq's toolchain (mq-crawl for fetching/crawling/JS rendering, mq for HTML-to-Markdown selector-based extraction, http() for in-query requests). Use when the user wants to scrape a URL, pull structured data out of a webpage, crawl a site, or turn HTML into…
larksnap-fetch
A bridge for downloading Feishu/Lark documents or ordinary webpages into local files, with options such as Markdown, HTML, or PDF. Feishu, also called Lark, is a workplace collaboration platform.