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/damusix/atomic-claude/atomic-cli-contribnpx skills add damusix/atomic-claude --skill atomic-cli-contribgit clone --depth 1 https://github.com/damusix/atomic-claudeWrote 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/damusix/atomic-claude/atomic-cli-contrib)<a href="https://agentmods.dev/skills/damusix/atomic-claude/atomic-cli-contrib"><img src="https://agentmods.dev/badge/skills/damusix/atomic-claude/atomic-cli-contrib.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 | $0.00138 | $0.05047 |
| Opus 5 | $0.00069 | $0.02524 |
| Sonnet 5 | $0.00028 | $0.01009 |
| Haiku 4.5 | $0.00014 | $0.00505 |
Grade B, and why
atomic-cli-contrib scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
The `outputstyle.*` and `settingsjson.*` helpers expect `scopeRoot` to be the directory that *contains* `.claude/`. They internally resolve `<scopeRoot>/.claude/settings.json`. How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
atomic-cli-contrib
Project-local skill for working on the atomic CLI in this repo. Captures conventions that emerged from the doctor, validate, and config work, plus the prompt-layer extraction. Read this before adding subcommands, flags, prompts, or new internal packages.
This skill is contributor-scope only. It lives under .claude/skills/ and is auto-loaded for sessions in this repo. It is not bundled (see atomic/internal/bundlemirror/mirror.go — only context/skills/atomic-*/ ships).
1. Interactive prompts go through internal/prompt/
- Single surface. Every interactive prompt — install flows, doctor
--fix, futureatomic config, anything new — callsinternal/prompt.Confirmorinternal/prompt.Select[T]. No directhuh.*calls outside the prompt package. Nobufio.Scannerprompters. - Why. One swap point when
huhchanges API. Consistent TTY detection. Consistent abort handling. - Sentinels. Callers branch on
errors.Is(err, prompt.ErrNonInteractive)(no TTY → skip path) anderrors.Is(err, prompt.ErrAborted)(Ctrl+C → distinct from "No"). Never collapse abort into decline. - Doctor adapter. The doctor's
Prompterinterface lives separately so the--fixloop can have its own decision shape (DecisionYes/DecisionNo/DecisionSkip/DecisionAbort). The adapter (doctor/stdin_prompter.go) translates frominternal/prompterrors. Mirror the adapter pattern if you build a new prompt-consuming subsystem.
2. Testable seams via function-field structs
-
Pattern. For any subsystem that calls external collaborators (filesystem, network, prompt, time), define a struct of function fields:
type MyStep struct { Classify func(scopeRoot, want string) (Result, error) Write func(scopeRoot, value string) error Confirm func(title, desc string, def bool) (bool, error) Logger io.Writer AssumeYes bool }Default factory wires production deps. Tests inject stubs.
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 · 273 lines · 138 tokens per session scan B 52a1e13d452b
atomic-cli-contrib is a skill published in the GitHub repository damusix/atomic-claude (83 stars, last pushed 9d ago), licensed MIT. It adds 138 tokens to every session and 5,047 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hns-moaiadk-patterns
Skill "hns-moaiadk-patterns" from modu-ai/moai-adk, covering moai-adk-go domain patterns, architecture quick reference, key source paths, pipeline specialist delegation map and template-first build cycle.
agentic-development
Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js).
ring:adopting-lib-commons-huma-wrapper
Adopting the lib-commons/v5 shared Huma (OAS 3.1) OpenAPI wrapper + RFC 9457 problem model (commons/net/http/{openapi,problem}) in a Lerian Go service: wire openapi.New/ServeSpec + problem.Install (central >=500 scrub) on BOTH runtime and spec-gen paths, the per-rail problem.MapError flex seam, and rename-only spec…
ring:fixing-lint
Fixing lint to a clean state: runs the linter, groups reported issues into independent streams, and dispatches one parallel fixer agent per stream (ring:backend-go for Go, ring:general-purpose otherwise), iterating until clean. Use when a codebase has lint errors across multiple files. Skip for a single error (fix…
ring:auditing-dependency-security
Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…
axum-idioms
Axum HTTP framework patterns — routing, extractors, middleware, state management. For Rust see rust-idioms.