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/subagent-implementation)<a href="https://agentmods.dev/commands/damusix/atomic-claude/subagent-implementation"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/subagent-implementation/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/subagent-implementation"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/subagent-implementation.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 | $0.00045 | $0.00400 |
| Opus 5.5 | $0.00018 | $0.00160 |
| Sonnet 5.5 | $0.00009 | $0.00080 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
subagent-implementation 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 orchestrate; you do not write the code. Fresh-context subagents do, and the scratchpad brief is their only handoff.
Policy
| Setting | Value |
|---|---|
| Writer | atomic-implementer |
| Entry | hand-off table, plus: no spec and the work is more than a small obvious change → /atomic-plan first |
| Worktree | ask (skip the question when the work is small) |
| Stuck | ask |
| Non-blockers | ledger |
| Finalize | verify, docs, audit, follow-ups, log, signals, report |
| Scratchpad purpose | implement |
| Ship | no |
{{ template "handoff" . }}
Understand
Dispatch atomic-investigator to map the surface (files, call sites, tests, conventions) unless the task names exact files. Lead it with atomic code explore "<area>" when an index exists. Read only what its file:line table says you need for scoping; do not implement.
Spec
Topic slug from the task. docs/spec/<topic>.md exists → it is the brief's source and its checkpoint table is the loop. Its body must be current before any dispatch: a decision in this conversation that superseded part of it is fixed in the spec, never worked around in the brief.
No spec and the work is small and obvious → say no spec; proceeding inline and continue with a one-checkpoint brief. Otherwise → hand off to /atomic-plan.
{{ 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 Changed · -227 lines · -8 tokens per session 1c83d9dcb387
- 1mo ago First seen · 268 lines · 53 tokens per session scan A 27498e11dbdb
subagent-implementation is a command published in the GitHub repository damusix/atomic-claude (112 stars, last pushed 9d ago), licensed MIT. It adds 45 tokens to every session and 400 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 2026-08-30.
Other commands, from other repositories
save
Save current work state for next session. Creates/updates .planning/ files (CHECKPOINT.md, STATE.md, settings.json) so Heimdall resumes with full context. NOT a rewind — saves forward progress. Run before closing a session or at any milestone.
designmatch
Bootstrap the designmatch skill in a React Native project from a Claude Design link. Auto-imports the Visual QA stub helper (visual-qa.ts), writes default state.vqa.json, registers the canonical source, updates .gitignore, and prints the wiring snippet. Use when starting visual-parity work on a new RN screen or when…
maintain
Run automated maintenance — seeker finds bugs from pod logs and raises GitHub issues, fixer picks them up and creates PRs. Can run as a one-shot or scheduled via /schedule.
bench
Reproduce the public benchmark table on your own machine (spec S-5). Runs a fixed suite of coding tasks under two arms — raw Claude Code vs Heimdall — and PRODUCES real numbers (tokens, wall time, tests passing, cost) by actually running them. Never hardcodes results. Safe by default (dry mode: validates the suite +…
autonomy
Set Heimdall autonomy (1=Guided, 2=Checkpoint, 3=Full Auto) — how much the agent does before asking. Use with a number, +/- to cycle, or no argument to show current.
level
Deprecated alias for /hmd:autonomy. Sets Heimdall autonomy (1=Guided, 2=Checkpoint, 3=Full Auto). Still works; prints a one-line rename notice.