Borrowing it
Nothing to install: this file belongs to alexjbarnes/cockpit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alexjbarnes/cockpit/main/.claude/skills/implement-issue/SKILL.mdgit clone --depth 1 https://github.com/alexjbarnes/cockpitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alexjbarnes/cockpit/implement-issue)<a href="https://agentmods.dev/skills/alexjbarnes/cockpit/implement-issue"><img src="https://agentmods.dev/badge/skills/alexjbarnes/cockpit/implement-issue/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alexjbarnes/cockpit/implement-issue"><img src="https://agentmods.dev/badge/skills/alexjbarnes/cockpit/implement-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00132 | $0.06222 |
| Opus 5.5 | $0.00053 | $0.02489 |
| Sonnet 5.5 | $0.00026 | $0.01244 |
| Haiku 4.5 | $0.00013 | $0.00622 |
Grade C, and why
implement-issue scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .next # Next resolves the workspace root at the parent dir and can serve the MAIN repo's stale .next; clear it or the reviewer sees old code Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Checks take a few seconds to register after the PR is created; if `gh pr checks` reports none yet, poll briefly with `curl` (foreground `sleep` is blocked) and retry, then watch. How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement a cockpit issue
The Implementation stage of the pipeline. The issue description already holds a precise, human-approved plan (produced by refine-issue, reviewed, and approved at the issue-level Plan Review gate). This skill executes that plan, then adversarially reviews its own code inline, in one warm run.
The plan is the contract. Follow it. It names the files, symbols, and exact changes. Do not redesign it. If a step is wrong or blocked by reality, make the minimal correct change and record the deviation rather than improvising silently.
Implementation and code review are one stage. The skill codes the plan, then dispatches the code-reviewer agent against its own diff and fixes what it finds, looping in warm context. There is no separate code-review stage in the autonomous pipeline. The issue moves Implementation -> Code Review (the code-level gate) directly.
Input
Either an explicit issue key, or none (the skill selects one).
- An issue key was given (e.g. CK-12): use it.
- No key, pipeline mode (a scheduled job ran the skill): select one.
mcp__cockpit-config__list_issueswithstatus: "Implementation Ready". If there are none, stop, there is no work this run, do nothing else. Otherwise pick exactly ONE, highest priority then oldest byupdatedAt, and implement only that. Ignore the rest; a later run picks them up. Selecting one and immediately moving it toImplementation(step 3) is what stops two runs grabbing the same issue. - No key, interactive mode (a human ran the skill):
list_issueswithstatus: "Implementation Ready"and ask which one to implement. Do not auto-pick.
This is why a scheduled implementation job needs no selection logic in its prompt. "Run the implement-issue skill" is the whole job; the skill picks the issue.
Invocation modes
- Pipeline (autonomous): an issue enters
Implementation Readyand an agent runs the skill end to end. Perform all status transitions. Push and open the PR without waiting for a human. - Interactive: a human runs the skill directly (e.g. "implement CK-12"). Same flow, but confirm with the human before the outward-facing actions: pushing the branch and opening the PR.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 242 lines · 132 tokens per session scan C a93f83f2ced4
implement-issue is a skill published in the GitHub repository alexjbarnes/cockpit (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 132 tokens to every session and 6,222 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
version-bump
Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging, GitHub releases, and changelog generation. npm publishing is done by the tag-triggered GitHub Actions workflow through…
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
emerging-techniques-model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
release
Fully automate a release with version-bump and childhood.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.