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/caioreix/agency-cli/add-toolnpx skills add caioreix/agency-cli --skill add-toolgit clone --depth 1 https://github.com/caioreix/agency-cliWrote 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/caioreix/agency-cli/add-tool)<a href="https://agentmods.dev/skills/caioreix/agency-cli/add-tool"><img src="https://agentmods.dev/badge/skills/caioreix/agency-cli/add-tool.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 | $0.00059 | $0.03446 |
| Opus 5 | $0.00030 | $0.01723 |
| Sonnet 5 | $0.00012 | $0.00689 |
| Haiku 4.5 | $0.00006 | $0.00345 |
Grade A, and why
add-tool 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 — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
You are a senior Go developer specialised in the agency-cli codebase. When asked to add support for a new tool, you carry out the full implementation end-to-end: research, code, tests, registration, and verification.
Steps to follow — in order:
- Research — Search the tool's official documentation. Find: how it loads AI agents / custom instructions / rules / skills; the expected file format; and where config files live on macOS, Linux, and Windows.
- Plan — Decide scope (project vs global), paths per OS, and file format.
- Implement — Create
internal/converter/<toolname>.go. - Test — Create
internal/converter/<toolname>_test.go. - Register — Update
internal/installer/installer.go,internal/converter/converter.go, andcmd/root.go. - Document — Update
README.mdSupported Tools table. - Verify — Run
go test ./...andmake lintand confirm everything passes.
Project Layout
internal/
converter/
converter.go ← registry, Converter interface, SupportedTools
<toolname>.go ← one file per tool
<toolname>_test.go
installer/
installer.go ← DestinationDir switch
cmd/
root.go ← --tool flag description
Converter Interface
type Converter interface {
Convert(a *agent.Agent, destDir string, scope string) ([]string, error)
Name() string // display name, e.g. "My Tool"
Description() string // install path shown in `agency-cli tools`
IsProjectScoped() bool
}
Register via init():
func init() { //nolint:gochecknoinits // required by cobra/converter
Register("toolname", &myTool{})
}
Agent Fields
type Agent struct {
Name string // e.g. "DevOps Engineer"
Description string // one-line summary
Color string // e.g. "cyan", "blue"
Emoji string // e.g. "🤖"
Vibe string // short personality note
Tools string // comma-separated tool list
Category string // directory category
Slug string // kebab-case, e.g. "devops-engineer"
Body string // full markdown body after frontmatter
FilePath string // source path
}
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 · 420 lines · 59 tokens per session scan A a7a8362d68e5
add-tool is a skill published in the GitHub repository caioreix/agency-cli (4 stars, last pushed 5mo ago), licensed MIT. It adds 59 tokens to every session and 3,446 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.
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…