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/itaywol/adeptability/adept-contributingnpx skills add itaywol/adeptability --skill adept-contributinggit clone --depth 1 https://github.com/itaywol/adeptabilityWrote 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/itaywol/adeptability/adept-contributing)<a href="https://agentmods.dev/skills/itaywol/adeptability/adept-contributing"><img src="https://agentmods.dev/badge/skills/itaywol/adeptability/adept-contributing.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 | $0.00048 | $0.00675 |
| Opus 5 | $0.00024 | $0.00338 |
| Sonnet 5 | $0.00010 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
adept-contributing 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributing to adept
You are working on the adept CLI itself (Go 1.25, module
github.com/itaywol/adeptability). Read AGENTS.md for architecture and
invariants; this skill is the operational checklist.
Build & run
go build ./...
go build -o /tmp/adept ./cmd/adept && /tmp/adept --help
Gates you MUST pass before opening a PR (same as CI)
gofmt -l . # must print nothing → fix with: gofmt -w .
go vet ./...
golangci-lint run # config: .golangci.yml
go test -race ./...
go test -run E2E ./cmd/adept # end-to-end against a freshly built binary
If any gate fails, fix it before pushing — CI runs the identical set on ubuntu/macos/windows.
Where things live
| You're changing… | Go there |
|---|---|
| public types / interfaces / sentinel errors | pkg/adept/ (types only — no behavior) |
| canonical field shape | pkg/adept/ struct tags and pkg/adeptschema/*.schema.json together |
| a command | internal/cli/commands_*.go; wire deps in internal/cli/deps.go |
| a harness renderer | internal/render/<id>/ + golden fixtures in its testdata/ |
| sync / drift logic | internal/harness/orchestrator.go |
| 3-way merge | internal/merge/ |
| safety scanner | internal/scan/ |
Conventional commits (release-please reads these)
feat: → minor · fix:/perf: → patch · feat!:/BREAKING CHANGE: → major ·
refactor:/docs:/chore:/test:/ci: → no release. The squash-merge title becomes the
changelog entry, so write it well.
Conventions
- Wrap errors with context:
fmt.Errorf("doing X: %w", err). Match witherrors.Isagainst the sentinels inpkg/adept/errors.go— never on error strings. Add new sentinels there. - No package-level state, no
init()side effects: dependencies flow through*Deps. - New behavior ships with tests; bug fixes ship with a regression test. Update golden fixtures in the same PR when output changes, and say why in the message.
- Don't hand-edit
CHANGELOG.md,.release-please-manifest.json, or version strings — release-please owns them.
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 · 64 lines · 48 tokens per session scan A d37ff704f6a2
adept-contributing is a skill published in the GitHub repository itaywol/adeptability (9 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 675 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 2026-08-31.
Other skills, from other repositories
pr-review
AUTHOR SKILL (internal to microsoft/aspire-skills). Reviews pull requests into this repo for problems only — bugs, regressions, missing eval coverage, frontmatter or routing damage, plugin-manifest drift, hook safety, and other concrete issues. Drives a six-step workflow: identify the PR, ensure the branch is…
architecture-cleanup
Use when performing a behavior-preserving architectural cleanup or refactor on a codebase and you need strict guardrails against changing functionality, building a framework, or rewriting tests to fit the new design.
aspire-orchestration
../../../../../skills/aspire-orchestration/SKILL.md.
aspire-deployment
../../../../../skills/aspire-deployment/SKILL.md.
aspire-init
../../../../../skills/aspire-init/SKILL.md.
aspire-monitoring
../../../../../skills/aspire-monitoring/SKILL.md.