harrylettering/codememory/codememory-mark-constraint
Claude Code and agent skill by harrylettering/codememory
- community
Checking that the SKILL.md file is still in the repository.
Use this skill to durably record a hard constraint or invariant that the work must respect. Invoke when the user states a must-not-break rule, a compatibility boundary, a performance budget, a security/compliance requirement, or any other guardrail that should outlive compaction. Do NOT invoke for soft preferences, style nudges, or constraints already captured earlier in the session.
Install
npx vskill@latest install harrylettering/codememory/codememory-mark-constraintSKILL.md
CodeMemory — Mark Constraint
Persists a single hard constraint into the CodeMemory memory store via the per-session daemon. The result is a Memory Node tagged constraint + requirement that future turns can consult before making decisions.
When to Use
Invoke this skill when, in the current turn, the user (or you, after agreement) established a guardrail. Good signals:
- "Don't break the public API."
- "We need to keep p99 latency under 50 ms."
- "All writes must go through the daemon — no direct sqlite from hooks."
- "This file must remain backwards-compatible with v0.1 clients."
- A migration plan that explicitly excludes a region of code from changes.
Do NOT invoke for:
- Stylistic preferences ("use camelCase") — those belong in CLAUDE.md or feedback memory.
- Constraints already marked in this session, unless materially revised (then supersede).
- Soft suggestions phrased as "might be nice".
How to Invoke
Run the wrapper script with requirement as the endpoint and a JSON payload. Required fields: kind: "constraint", requirement. Optional: details, acceptance_criteria (array), supersedesNodeId, sourceToolUseId.
Run the command exactly as written: Claude Code fills in ${CLAUDE_SESSION_ID} and ${CLAUDE_PLUGIN_ROOT}, and the session id is how the mark reaches this session's daemon and no other. On success it returns JSON like {"ok":true,"conversationId":...,"memoryNodeId":"requirement-constraint-tool-..."}.
Authoring Guidance
- `requirement`: one durable sentence stating the rule. Phrase as an invariant ("must / never / only").
- `details`: short paragraph explaining the why — usually a past incident, a compliance ask, or a performance budget. The why is what lets future turns judge edge cases.
- `acceptance_criteria`: concrete checks that the constraint is being honored. Optional but recommended.
- `supersedesNodeId`: set when an older constraint node is being replaced.
- `sourceToolUseId`: pass the originating tool_use id when known so retries collapse onto the same node.
After invoking, continue the work — do not echo the constraint back at the user.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/codememory-mark-constraint/SKILL.md
Popularity
- Repository stars
- 138
- Repository forks
- 11
- 7-day trend score
- 25
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 18 May 2026, 5 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/harrylettering/codememory/codememory-mark-constraint)