decision
Record an architectural/product decision in the project's Decisions Log (append-only, newest first).
Skill by mateim4
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mateim4-decision
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/decision
What's inside
- Skill name
decision- Description
- Record an architectural/product decision in the project's Decisions Log (append-only, newest first). Use when a choice has been made and should be captured durably.
- License
- MIT
- Instructions
- 30 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Record a decision 1. Locate the Decisions Log (the `decisions_log` note in the vault, e.g. `00 - Foundations/Decisions Log.md`). If none exists, create one from the AgentStrap template and tell the user. **Do not read the whole file.** It is append-only and grows without bound. Read the top of it — the usage note, the table of contents, and the first entry or two — which is all you need to insert correctly. A full read must be a deliberate choice, not a side effect of recording a decision. 2. Insert a new entry directly below the `---` that follows the table of contents (newest first): ``` ## YYYY-MM-DD — <title> - **Decision:** what we chose. - **Why:** the reasoning. - **Alternatives:** options considered and rejected (and why). - **Decided by:** <name>. ``` 3. **Add its row to the top of the table of contents** in the same edit — an entry without a ToC row is unfindable: ``` | YYYY-MM-DD | [[#YYYY-MM-DD — <title>\|<title>]] | ``` If the log has no table of contents yet, add one (see the AgentStrap template) rather than skipping this step. 4. Fill it from the conversation; confirm the title and the "Decided by" with the user if unclear. If the user overrode your recommendation, record that explicitly under **Alternatives** — a rejected recommendation is the most useful thing in the log later. 5. If this decision resolves an entry in **Open Questions**, remove that entry from the register (it now lives here) and note the migration. 6. **Amend what this decision contradicts** (working rule: shipping means amending, not just appending). If it changes a feature spec's status, a README claim, or an index note, fix that text in the same turn. A Decisions Log entry alone is not documentation. 7. Keep it factual and short. Save — the continuity hooks will sync it.
From mateim4/agentstrap-v2, MIT.
More from mateim4/agentstrap-v2
- 0.524score
handoff
mateim4
Force a full handoff refresh now — write a thorough narrative of where work stands into HANDOFF.md so the next session (or device) resumes cleanly.
SkillBFreshness: BClaude Code +9 - 0.521score
working-rules
mateim4
The AgentStrap PM-first collaboration contract — how Claude should drive an AgentStrap project.
SkillBFreshness: BClaude Code +9 - 0.520score
bootstrap
mateim4
Bootstrap or sanity-check an AgentStrap workspace in this project — idempotent and non-destructive.
SkillBFreshness: BClaude Code +9 - 0.474score
audit
mateim4
Run the AgentStrap audit swarm over the codebase — fan out specialist reviewers in parallel, then consolidate into a deduped P0–P3 report.
SkillCFreshness: CClaude Code +9 - 0.474score
release
mateim4
Run the AgentStrap release pipeline — bump all version files, finalize the changelog, build, gate on tests, tag, and write checksums.
SkillCFreshness: CClaude Code +9 - 0.471score
security-audit
mateim4
Focused security audit — runs the security + adversarial reviewers with STRIDE and deployment-context severity, then consolidates.
SkillCFreshness: CClaude Code +9 - 0.471score
open-question
mateim4
Add or resolve an entry in the project's Open Questions register.
SkillCFreshness: CClaude Code +9 - 0.467score
consolidate-findings
mateim4
Reduce step for the audit swarm — dedupe findings from multiple reviewers, assign stable IDs, normalize to P0–P3, and group into prioritized batches with a…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 9, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mateim4/agentstrap-v2
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mateim4
- 0.524score
handoff
mateim4
Force a full handoff refresh now — write a thorough narrative of where work stands into HANDOFF.md so the next session (or device) resumes cleanly.
SkillBFreshness: BClaude Code +9 - 0.521score
working-rules
mateim4
The AgentStrap PM-first collaboration contract — how Claude should drive an AgentStrap project.
SkillBFreshness: BClaude Code +9 - 0.520score
bootstrap
mateim4
Bootstrap or sanity-check an AgentStrap workspace in this project — idempotent and non-destructive.
SkillBFreshness: BClaude Code +9 - 0.474score
audit
mateim4
Run the AgentStrap audit swarm over the codebase — fan out specialist reviewers in parallel, then consolidate into a deduped P0–P3 report.
SkillCFreshness: CClaude Code +9 - 0.474score
release
mateim4
Run the AgentStrap release pipeline — bump all version files, finalize the changelog, build, gate on tests, tag, and write checksums.
SkillCFreshness: CClaude Code +9 - 0.471score
security-audit
mateim4
Focused security audit — runs the security + adversarial reviewers with STRIDE and deployment-context severity, then consolidates.
SkillCFreshness: CClaude Code +9
Cite this page
decision skill. Agent Mart. https://agentmart.dev/skills/mateim4-decision (last updated 2026-10-24)