Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/zhpeng24/devkit/github-create-issuenpx skills add zhpeng24/devkit --skill github-create-issuegit clone --depth 1 https://github.com/zhpeng24/devkitWhat 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 | $0.00045 | $0.00769 |
| Opus 5 | $0.00023 | $0.00385 |
| Sonnet 5 | $0.00009 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
github-create-issue scanned grade A with 0 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adaptive GitHub Issue Creation
Create the smallest Issue that preserves the current SIES decision. Do not force discovery, experiments, Engineering, and learning into one static seven-section template.
Select an Issue Profile
Read references/issue-profiles.md and select by the Issue's immediate purpose:
| Purpose | Profile |
|---|---|
| Define a product or system Outcome | Goal / Product |
| Resolve a consequential unknown | Exploration |
| Produce evidence with a minimal artifact | Prototype |
| Deliver a selected solution or repair | Engineering / Bug |
| Propose a reusable system improvement | Learning |
The profile may change as evidence grows. Update or comment on the existing tracking Issue rather than creating a new Issue for every SIES phase.
Common Quality Gate
Before creation, confirm:
- Primary Outcome: one result owns the Issue, even if it spans several phases;
- Current decision: the Issue states what must be decided or delivered now;
- Bounded uncertainty: unknowns are explicit rather than hidden as facts;
- Evaluable evidence: success, failure, or stop can be observed;
- Traceability: known Issue, PR, ADR, incident, or user-report links exist;
- No duplicate: an existing open Issue does not already own the Outcome.
An Exploration Issue need not be implementation-ready. An Engineering Issue must be.
Split by Independence
Create child Issues only when work can be decided, rejected, shipped, or parallelized independently. A single tracking Issue may legitimately contain Goal, Exploration, Evaluation, and Engineering history for one Outcome.
Authorization
- Explicit “create”, “submit”, “直接建” or equivalent language authorizes the GitHub write; do not add a duplicate preview gate.
- Draft-only or analysis requests do not authorize creation.
- Ask one question only when a missing answer changes the primary Outcome, evaluation, scope, or irreversible impact.
Labels
Preserve repository labels when they already express the work. Common labels:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 99 lines · 45 tokens per session scan A 64d09bcb9208
github-create-issue is a skill published in the GitHub repository zhpeng24/devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 769 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…