Install
$ agentstack add skill-tartinerlabs-skills-update-project ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
You keep project documentation synchronized with recent code changes and git commits.
Run after significant code changes, before a release, or whenever docs may be stale.
Read individual rule files in rules/ for detailed requirements.
Detect which agent the project targets and maintain its instruction file accordingly: CLAUDE.md (Claude Code), AGENTS.md (Codex, OpenCode, and the cross-agent standard), or both. Component directories follow the same split — .claude/ for Claude Code, .agents/ for the cross-agent convention.
Rules Overview
| Rule | Impact | File | |------|--------|------| | Project instructions | HIGH | rules/project-instructions.md | | README.md | HIGH | rules/readme-md.md | | Agents | MEDIUM | rules/agents.md | | Skills | MEDIUM | rules/skills.md | | Rules | MEDIUM | rules/rules.md |
Workflow
Step 1: Detect
- Run
git log --oneline -20andgit diffto identify recent changes - Check which agent instruction files exist (
CLAUDE.md,AGENTS.md) and whether README.md exists (create if missing) - Scan both
.claude/and.agents/foragents/*.md,skills/*/SKILL.md, andrules/*.mdfiles - Compare documented instructions against actual project state to find stale sections
- Flag any new tools, removed dependencies, changed paths, or renamed commands
Step 2: Update
Read the relevant rule file for each document and apply updates:
rules/project-instructions.mdfor CLAUDE.md / AGENTS.md changesrules/readme-md.mdfor README.md changesrules/agents.mdfor.claude/agents/or.agents/agents/changesrules/skills.mdfor.claude/skills/or.agents/skills/changesrules/rules.mdfor.claude/rules/or.agents/rules/changes
Step 3: Validate
- Run project commands mentioned in docs to verify they work
- Check that instructions match current project setup
- Ensure the agent instruction file (CLAUDE.md / AGENTS.md), README.md, agents, skills, and rules complement each other without duplication
- If both CLAUDE.md and AGENTS.md exist, keep shared guidance consistent between them rather than duplicating divergent instructions
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: tartinerlabs
- Source: tartinerlabs/skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.