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/agentculture/fleet-cli/cicdnpx skills add agentculture/fleet-cli --skill cicdgit clone --depth 1 https://github.com/agentculture/fleet-cliWhat 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 | $0.00142 | $0.02612 |
| Opus 5 | $0.00071 | $0.01306 |
| Sonnet 5 | $0.00028 | $0.00522 |
| Haiku 4.5 | $0.00014 | $0.00261 |
Grade C, and why
cicd 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 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
to a later PR, don't refuse). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`python3` (stdlib only), `curl` (used by `pr-status.sh`). This is a copy
91% identical to cicd — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI/CD — fleet-cli edition
devex pr (in agentculture/devex) is the upstream for the
five core PR-lifecycle verbs — lint, open, read, reply,
delta. Steward used to vendor parallel scripts for each; in 0.12.0
those vendored copies were dropped in favor of delegating to devex.
What's left in this skill is the steward-specific gating layer:
status— SonarCloud quality gate, OPEN issues, hotspots, deploy preview URL, unresolved-inline-thread tally.await— composesdevex pr read --waitwithstatusand gates on SonarERROR/ unresolved threads. The single command to run after pushing a fix when you want "wake me when this PR is triage-able."
Those two are the steward unique surface today. The await combo verb
landed natively in devex
(devex#41, now
closed); the gate extras that aren't yet native — SonarCloud hotspots,
deploy-preview URL, an explicit resolved/unresolved thread tally — are
tracked upstream in
devex#52 and
migrate out of this skill once they land.
The workflow is encapsulated in scripts/workflow.sh — follow that
(or call devex pr directly).
The devex inversion (upstream-as-consumer)
One consumer is special: devex itself, the repo that owns devex pr.
Vendoring this skill there verbatim would re-vendor bash that just wraps the
Python devex already ships, so devex vendors it adapted-thin
(devex#53):
workflow.sh is the only script and it forwards
lint | open | read | reply | delta | await straight to the native
devex pr <verb> — including the native devex pr await combo verb (devex
0.21.0). The steward status / await shell extensions and the vendored
helpers (pr-reply.sh, _resolve-nick.sh, portability-lint.sh) are all
redundant there, each superseded by a native verb. For that one consumer the
skill collapses to a pure delegate.
What ships with it
5 files 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.
- 2d ago First seen · 209 lines · 142 tokens per session scan C 73aa62d03a51
cicd is a skill published in the GitHub repository agentculture/fleet-cli (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 142 tokens to every session and 2,612 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (tells the agent never to refuse, makes network calls). It is 91% identical to cicd, differing in 6 lines, and is treated as a copy.
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…