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.
git 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/commands/damusix/atomic-claude/implement)<a href="https://agentmods.dev/commands/damusix/atomic-claude/implement"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/implement/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/damusix/atomic-claude/implement"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/implement.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00061 | $0.00405 |
| Opus 5.5 | $0.00024 | $0.00162 |
| Sonnet 5.5 | $0.00012 | $0.00081 |
| Haiku 4.5 | $0.00006 | $0.00040 |
Grade A, and why
implement 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 1mo 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.
What it actually says
You write the code here. The reviewer dispatch after each checkpoint is the only independent review the work gets; it is never skipped, batched to the end, or replaced by your own suite run.
$ARGUMENTS: [<task>]. Empty is normal; the task is already in the conversation.
Policy
| Setting | Value |
|---|---|
| Writer | main agent |
| Entry | hand-off table, plus: the context is not already here (cold start, resumed session, unread surface), or the work would crowd it out → /subagent-implementation |
| Worktree | ask, only when the tree is clean; otherwise say dirty tree, staying in place |
| Stuck | ask |
| Non-blockers | ledger |
| Finalize | verify, docs, audit, follow-ups, log, signals, report |
| Scratchpad purpose | implement |
| Ship | no |
{{ template "handoff" . }}
Checkpoints
Declare them before writing code and state the list to the user. A spec's checkpoint table is the list (fix its body first when this conversation superseded it). Without a spec, split the task into checkpoints, one logical change each, however many files. More than six means the work belongs in /subagent-implementation. Mid-loop, little remaining context or a checkpoint list that has grown past the declaration → hand off to /subagent-implementation (STATE.md records the checkpoints and SHAs).
{{ template "worktree-setup" . }}
{{ template "implement-loop" . }}
{{ template "loop-finalize" . }}
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.
- 1mo ago First seen · 37 lines · 61 tokens per session scan A 7c47e451b6a5
implement is a command published in the GitHub repository damusix/atomic-claude (112 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 405 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-17.
Other commands, from other repositories
dream
Overnight autoresearch + maintainer sweep that surfaces a MORNING REPORT — suggested changes, issues raised with fixes, and kept improvements. Shadow-first; never auto-pushes. Runs on-demand or scheduled for off-hours.
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
address-pr-feedback
Systematically address PR review comments. Fetches all threads, categorizes by status (acknowledged, silently fixed, unaddressed), and guides user through posting replies and implementing fixes with explicit approval.
create-pr
Create a pull request with proper template discovery and population.
code-review-give
Give mode for code-review: Review someone else's code with multi-pass analysis and structured recommendations.