Install
$ agentstack add skill-codagent-ai-agent-skills-task-compliance ✓ 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.
About
Task Compliance
Review the implementation against the task file(s). Extract every spec scenario (WHEN/THEN) and every Done When criterion, then verify each one was addressed. Report what's missing.
Review Process
1. Extract Checklist
From each task file, extract every:
- Spec scenario (WHEN/THEN)
- Done When criterion
- Explicit instruction in the Background or Goal sections
This is your checklist. Every item must be accounted for.
2. Check Compliance
For each checklist item, check whether the implementation addresses it.
Classify each item:
- Addressed — the implementation covers this
- Missed — no evidence this was addressed
- Partially addressed — attempted but incomplete or incorrect
When you're unsure, read the actual code in the repository to verify before classifying. Do not mark something as missed without checking the code first.
3. Report
Present your findings:
## Task Compliance
### Addressed
- [Scenario/criterion] — [evidence]
### Gaps
- [Scenario/criterion] — [what's missing or incomplete]
Guardrails
- Do not mark a scenario as missed without checking the code first. It may have been implemented without being narrated in the conversation.
- Report only. Do not fix gaps — surface them for the human to decide how to proceed.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Codagent-AI
- Source: Codagent-AI/agent-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.