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/chenweil/skillcaddy/skillcaddy-managernpx skills add chenweil/skillcaddy --skill skillcaddy-managergit clone --depth 1 https://github.com/chenweil/skillcaddyWrote 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/chenweil/skillcaddy/skillcaddy-manager)<a href="https://agentmods.dev/skills/chenweil/skillcaddy/skillcaddy-manager"><img src="https://agentmods.dev/badge/skills/chenweil/skillcaddy/skillcaddy-manager.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.01612 |
| Opus 5 | $0.00026 | $0.00806 |
| Sonnet 5 | $0.00010 | $0.00322 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade A, and why
skillcaddy-manager 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 4d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skillcaddy Manager
Treat Skillcaddy as a central skill library with explicit project/global/Hermes symlink activation. Keep one execution loop across every branch: state -> route -> preflight -> act -> verify.
Core Loop
- Resolve the Skillcaddy repository and target project. Default the project to the current working directory only when the user did not provide one.
- Complete when both absolute paths are known.
- For recommendations, audits, or mutations, read
GET /api/state?projectPath=<encoded-path>. For source acquisition, updates, or migration, also inspect the source registry withnpm run source -- listandnpm run source -- inspect <source-id>. If the server is unavailable, inspect the equivalent paths listed under Core Model.- Complete when repository, source registry, project, global, Hermes, Claude, metadata, and
advicestate relevant to the request are known.
- Complete when repository, source registry, project, global, Hermes, Claude, metadata, and
- Route to the required branch and load only its reference; load multiple references only when the request combines branches:
- Discovery, source acquisition/update/migration, enable/disable, audit, health, Git update, bootstrap, Web/TUI: OPERATIONS.md
- Recommendations: RECOMMENDATION_GUIDE.md
- Notes, tags,
autoEnable, migration, batch Chinese notes: METADATA.md - Complete when the selected branch, target identities, and completion criterion are explicit.
- For a mutation, apply the Mutation Gate before acting. Prefer the existing API, TUI, or repository commands over ad hoc filesystem changes.
- Complete when the preflight accounts for every affected item and all blocking ownership or alias issues are resolved.
- Execute the narrowest requested operation, rescan state, and report the observed result.
- Complete when the post-operation state proves every requested item succeeded, remained unchanged, was skipped, or failed with a stated reason.
Core Model
What ships with it
12 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.
- agents/openai.yaml 305 B
- references/featured-skills.json 17 KB
- references/METADATA.md 3.1 KB
- references/OPERATIONS.md 17 KB
- references/RECOMMENDATION_GUIDE.md 3.1 KB
- references/skill-platforms.json 1.7 KB
- scripts/check-conflicts.cjs 3.6 KB runs code
- scripts/check-global-skills.cjs 5.3 KB runs code
- scripts/translate-skill-notes.cjs 9.8 KB runs code
- scripts/version-manager.cjs 3.7 KB runs code
- scripts/view-recommendations.cjs 7.9 KB runs code
- skillcaddy.json 215 B
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.
- 4d ago First seen · 94 lines · 52 tokens per session scan A 595b74721528
skillcaddy-manager is a skill published in the GitHub repository chenweil/skillcaddy (24 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,612 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 2026-08-30.
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.
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…