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-code-stylenpx skills add itaywol/adeptability --skill adept-code-stylegit clone --depth 1 https://github.com/itaywol/adeptabilityWhat 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 | $0.00053 | $0.00733 |
| Opus 5 | $0.00026 | $0.00367 |
| Sonnet 5 | $0.00011 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
adept-code-style 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
adept code style
Conventions for Go in github.com/itaywol/adeptability. CI enforces formatting and lint;
the rest is reviewed.
Formatting & lint (enforced)
gofmt+goimports— tabs for indentation, grouped imports (stdlib / third-party / local). CI fails on any unformatted file.golangci-lint run(.golangci.yml):errcheck(incl. type assertions),staticcheck,govet,gocritic,revive(every exported symbol needs a doc comment),errorlint,nilerr,bodyclose,prealloc,unconvert,misspell,unused,ineffassign.
Errors
- Always wrap with context and
%w:fmt.Errorf("clone %s: %w", url, err). - Compare with
errors.Isagainst the sentinels inpkg/adept/errors.go(ErrSkillNotFound,ErrMergeConflict,ErrBudgetOverflow, …). Never match on error strings. Need a new category? Add a sentinel there. errcheckis strict — handle or explicitly_ =an ignored error, and say why if it isn't obvious. Don't drop an error that loses data.
Structure
- Composition root, no globals. Concrete implementations are wired behind interfaces into
*Depsininternal/cli/deps.go. No package-level mutable state, noinit()side effects. Take dependencies as parameters so code is testable with fakes/mocks. pkg/adeptis types-only. Keep it dependency-light and stable; behavior lives ininternal/. (Example:SkillIDPatternis a string inpkg/adept, compiled ininternal/canonical— don't add aregexpimport topkg/adept.)- Doc comments are full sentences starting with the symbol name (
// NewRoot builds …).
Readability
- Small, single-purpose functions; prefer early returns over deep nesting.
- Name things for what they are; avoid one-letter names outside tight loops/receivers.
- No magic numbers/strings — name on-disk paths and limits as constants (see
pkg/adept/constants.go). - Comments explain why, not what. Keep them in sync with the code — a stale comment is a bug.
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 · 59 lines · 53 tokens per session scan A c12bd1e2940a
adept-code-style is a skill published in the GitHub repository itaywol/adeptability (9 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 733 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
go-expert
Use this skill when writing or reviewing Go code. Covers Go idioms, concurrency patterns, error handling, project structure, testing, benchmarks, and production-grade Go standards.
rove
Use when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell. Also the ONLY channel for messaging another agent session on this machine — rove api send, never a peer/MCP side channel.
general-video
The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a…
changelog-generator
Draft Rove release notes as Changesets. Writes user-facing entries as .changeset/.md files for @sma1lboy/rove (consumed into packages/kobe/CHANGELOG.md at release time). Use when the user asks for "changelog", "release notes", "what changed", "add a changeset", or before cutting a version. Enforces Rove's no-soft-wrap…
pstack
Rigorous engineering mode for nontrivial work in this repo — a set of named principles plus the leaf skills that apply them. Use when the user says "pstack", "go deep", "be rigorous", "认真做", or when a task involves architecture, a real bug, a refactor, or anything the user will not be watching. Ported from…
hyperframes-core
The HyperFrames composition contract — build one renderable project. Use for composition structure, the data- timing attributes, class="clip", tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.