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/agentic-dev3o/devx-plugins/cinpx skills add agentic-dev3o/devx-plugins --skill cigit clone --depth 1 https://github.com/agentic-dev3o/devx-pluginsWhat 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 | $0.00039 | $0.01461 |
| Opus 5 | $0.00019 | $0.00731 |
| Sonnet 5 | $0.00008 | $0.00292 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
ci 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conventional Commit
Be autonomous. Commit the work this session produced without asking for confirmation. Do not halt on junk or unrelated files — exclude them, commit the rest, and report.
Workflow
-
Survey the working tree:
git status --short git branch --show-current -
Decide what belongs in this commit (see Selecting Files below). Sort every dirty path into one of four buckets:
- Commit — changes produced by the work done in this session (files you edited or created, plus their direct byproducts like lockfiles, generated output, or migrations).
- Exclude (secret) —
.env, keys, credentials. Never commit these; call them out explicitly (see Junk & Secret Detection). - Exclude (junk) — build artifacts, caches, dependencies, OS/editor cruft (see Junk & Secret Detection).
- Exclude (unrelated) — pre-existing dirty files unrelated to this session's work.
-
Stage only the Commit bucket, with explicit pathspecs — never
git add -Aorgit add .:git add -- <path1> <path2> ... git diff --cached --stat git diff --cached -
Analyze the staged diff — determine type, scope, subject.
-
Commit immediately (no confirmation needed). Add a second
-mfor a body when the change is non-trivial:git commit -m "<type>(<scope>): <subject>" -
Report:
- the commit hash and message,
- a short list of anything excluded and why — call out junk that should be added
to
.gitignoreand any secrets that were left uncommitted, as information for the user. Do not block on these.
Selecting Files
Prefer precision over completeness. The goal is a commit that matches the work you actually did this session.
- You have session context (you edited files in this conversation): stage exactly those files and their direct byproducts. Leave everything else for the user.
- No session context (e.g.
/devx-git:cirun cold at the start of a session): treat all dirty tracked + untracked paths as the Commit bucket, minus anything caught by Junk & Secret Detection. - Ambiguous (a dirty file might or might not relate to the work): if it plausibly belongs to the change, include it; if it clearly doesn't, exclude it and mention it in the report.
- Distinct concerns in one working tree: it's fine to stage only the cohesive subset that forms one logical commit and tell the user what you left for a follow-up commit.
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 · 160 lines · 39 tokens per session scan A 9d0bdc8f3d6f
ci is a skill published in the GitHub repository agentic-dev3o/devx-plugins (11 stars, last pushed 14d ago), licensed MIT. It adds 39 tokens to every session and 1,461 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 2026-08-30.
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.