j0k3r-dev-rgl/open-code-config-public/engram-pending-tasks
Claude Code and agent skill by j0k3r-dev-rgl/open-code-config-public
- community
Checking that the SKILL.md file is still in the repository.
user mentions pending, tech-debt, TODO, pendiente, deuda técnica, or asks about pending tasks. Normalizes Engram task tracking.
Install
npx vskill@latest install j0k3r-dev-rgl/open-code-config-public/engram-pending-tasksSKILL.md
The same SKILL.md was published earlier as j0k3r-dev-rgl/open-code-config-public/engram-pending-tasks.
Activation Contract
Load this skill when: user mentions pending, tech-debt, TODO, pendiente, deuda técnica, or asks about pending tasks. Normalizes Engram task tracking..
Before executing substantive work, read references/full-contract.md when it exists and the task needs details beyond this compact contract.
Hard Rules
- Preserve the original contract details in
references/full-contract.md; do not replace them with generic assumptions. - Keep the skill scope narrow: apply this skill only to the surface named in the description and reference.
- Escalate before changing product, architecture, persistence, security, or SDD phase semantics not explicitly covered.
- Do not use external URLs as primary authority; use local references and repo evidence.
Decision Gates
| If | Then | |
|---|---|---|
| The task is a small/read-only check | Use this compact contract and inspect only needed local files. | |
| The task changes behavior or architecture | Read references/full-contract.md before planning or editing. | |
| The task crosses another skill boundary | Load the more specific related skill or ask before proceeding. | |
| Required evidence is missing | Stop and report the missing evidence instead of inventing rules. |
Execution Steps
- Confirm the touched surface and whether
references/full-contract.mdis needed. - Apply hard rules and any detailed local reference rules before editing.
- Use the narrowest validation path available for the touched surface.
- Record evidence: files inspected, rules applied, validations run, and unresolved risks.
Output Contract
Return:
- Skill applied:
engram-pending-tasks. - Scope/surface handled.
- Whether
references/full-contract.mdwas read. - Hard rules and decision gates used.
- Validation or evidence collected, or why it could not be collected.
- Open risks, blockers, or follow-up actions.
References
references/full-contract.md— full detailed contract moved out of runtime body.
Security
- Security scanPassed, 95 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/engram-pending-tasks/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
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/j0k3r-dev-rgl/open-code-config-public/engram-pending-tasks)