Implements GitHub Issues based on existing execution plans.
Install
mkdir -p .claude/skills/coder && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16537" && unzip -o skill.zip -d .claude/skills/coder && rm skill.zipInstalls to .claude/skills/coder
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Implement a planned Pipeline GitHub Issue by number. Use when Codex is asked to execute an active plan end-to-end, update code/tests/docs, mark plan steps complete, run the relevant verification commands, and report results without editing issue labels, closing the Issue, moving the plan, or committing.Key capabilities
- →Implement a planned Pipeline GitHub Issue by number
- →Update code, tests, and documentation
- →Mark plan steps complete
- →Run relevant verification commands
- →Report results without editing issue labels or committing
How it works
The skill reads a GitHub Issue and its active execution plan, then follows the plan steps to implement the issue, update tests and docs, and run verification commands.
Inputs & outputs
When to use coder
- →Implementing planned GitHub issue
- →Updating tests and docs for issues
- →Running verification scripts
About this skill
Coder
Implement exactly one GitHub Issue. The manager owns lifecycle labels, commits, pushes, and plan archival.
Start and finish with:
MODEL: <model> | EFFORT: <effort>
Required Context
-
Read
AGENTS.md. -
Read the Issue and comments:
gh issue view <number> -c gh issue view <number> --json title,body,labels,assignees,url -
Read
.codex/skills/issue/SKILL.md. -
Read the active execution plan:
docs/exec-plans/active/issue-<number>-*.md.
If the caller explicitly says Flow: trivial-frontend, there may be no plan. In that case, work directly from the Issue body and comments.
Workflow
- Confirm the user supplied an Issue number.
- Read the Issue, comments, labels, and active plan.
- If no active plan exists and this is not
Flow: trivial-frontend, stop and report that planning is missing. - Implement the Issue end-to-end:
- Follow plan steps in order.
- Add or update tests where useful.
- Update docs listed in
Docs to Update. - If the Issue or plan references Figma, use it as an implementation reference.
- Mark completed plan steps as you go. Do not create a plan for trivial frontend mode.
- Run verification scaled to the changes:
- Rust changes:
cargo clippy --all -- -D warnings. - TypeScript or docs changes:
npx tsx scripts/lint-docs.ts. - Frontend changes: run the relevant frontend lint/build scripts from
package.jsonor package docs. - Run the repo's fast test workflow when available.
- Rust changes:
- Fix failures before reporting done. If blocked by environment or dependency failures, report exact commands and errors.
Rules
- Do not edit Issue labels, assign, close, commit, push, or move the plan to completed.
- Do not ask for approval during implementation; execute the plan.
- Respect existing code patterns and architecture boundaries.
- Do not fix unrelated bugs inline. Log them in
docs/exec-plans/known-bugs.mdwith date, location, symptom, root cause if known, and workaround. - Log intentional shortcuts or structural gaps in
docs/exec-plans/tech-debt-tracker.md. - If the plan is wrong or incomplete, use judgement, note the deviation in the final report, and comment on the Issue.
- Never revert user changes or unrelated worktree changes.
Trivial Frontend Mode
When the caller says Flow: trivial-frontend:
- Work from the Issue body and comments.
- Do not invent an execution plan.
- Keep changes self-contained to the frontend.
- Leave lint, build, and relevant tests green.
- Touch product docs only when behavior visibly changes.
Output
Report:
- Issue number and title
- What changed
- Tests added or updated
- Verification commands and pass/fail results
- Docs updated
- Plan deviations, blockers, or concerns
When not to use it
- →When the task involves editing issue labels
- →When the task involves committing or pushing changes
- →When the task involves moving the plan to completed
Limitations
- →Cannot edit Issue labels
- →Cannot commit or push changes
- →Cannot move the plan to completed
How it compares
This workflow automates the execution of a pre-defined plan for a GitHub Issue, unlike manual implementation that requires direct human oversight for each step.
Compared to similar skills
coder side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| coder (this skill) | 0 | 3mo | Review | Intermediate |
| agent-implementer-sparc-coder | 1 | 6mo | Review | Intermediate |
| scaffold-feature | 0 | 4mo | Review | Intermediate |
| deepwiki-rs | 25 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
agent-implementer-sparc-coder
ruvnet
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder
scaffold-feature
niklasbrandt
Scaffold a complete full-stack feature: FastAPI endpoint, dashboard Web Component, i18n keys, test stubs, and documentation checks.
deepwiki-rs
sopaco
AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.
rust-errors
EpicenterHQ
Rust to TypeScript error handling patterns for Tauri apps. Use when defining Rust errors that will be passed to TypeScript, handling Tauri command errors, or creating discriminated union error types.
lint
Azure
>-
code-review
jonatron55
Instructions for reviewing changes and ensuring quality before completion. Use when asking for a review or before committing changes.