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/sleeyax/promptfiles/implementnpx skills add sleeyax/promptfiles --skill implementgit clone --depth 1 https://github.com/sleeyax/promptfilesWhat 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 | $0.00056 | $0.01757 |
| Opus 5 | $0.00028 | $0.00879 |
| Sonnet 5 | $0.00011 | $0.00351 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
implement 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 2d 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.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Issue
Issue: $ARGUMENTS
Implement a specific issue from GitHub, GitLab, or Linear. Example invocations: /implement #1, /implement 2, /implement ENG-42.
Workflow
1. Extract the Issue Reference
Parse the issue reference from $ARGUMENTS. It identifies both the issue and the tracker it lives in:
#3→ issue3on the repo's git host4→ issue4on the repo's git hostENG-42(letters, dash, digits) → Linear issueENG-42- A
linear.app/…/issue/ENG-42/…URL → Linear issueENG-42 - A GitHub or GitLab issue URL → that issue, on that host
If no issue reference was provided, ask the user for one before proceeding.
2. Determine the Tracker
If step 1 matched a Linear identifier or URL, the tracker is Linear — skip the git remote check entirely. Linear is independent of where the code is hosted, so the remote says nothing about it.
Otherwise, run git remote -v to inspect the remote URLs and match against the host:
- Contains
github.com→ GitHub - Contains
gitlab.comor any GitLab instance (e.g. self-hosted) → GitLab - Otherwise, ask the user which tracker to use.
For GitHub/GitLab, also extract the owner/repo (GitHub) or group/project (GitLab) path from the remote URL — you'll need it to fetch the issue.
3. Fetch the Issue
Linear
The Linear MCP server is the only supported way to reach Linear — there is no CLI fallback, and no other tracker is a substitute.
If the Linear MCP tools are not in this session, stop before fetching anything and run claude mcp list to find out why. A session binds its MCP tools at startup, so the two failure modes need different fixes:
Not configured — no Linear server in the list. Adding one now cannot surface its tools in this session; it takes a restart. Tell the user to run claude mcp add --transport http linear https://mcp.linear.app/mcp, restart Claude Code, then re-run this skill — and stop the workflow. Offering to retry here would only fail again.
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.
- 2d ago First seen · 119 lines · 56 tokens per session scan A 390fcad56d39
implement is a skill published in the GitHub repository sleeyax/promptfiles (2 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 1,757 once invoked, about $0.0003 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.