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/report-issue)<a href="https://agentmods.dev/commands/damusix/atomic-claude/report-issue"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/report-issue/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/report-issue"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/report-issue.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 | $0.00022 | $0.00776 |
| Opus 5.5 | $0.00009 | $0.00310 |
| Sonnet 5.5 | $0.00004 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
report-issue 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prereqs
command -v gh— if missing: tell user to install (brew install gh/winget install --id GitHub.cli/ https://cli.github.com/) thengh auth login. Stop.gh auth status— if unauthed: tell usergh auth login. Stop.
Steps
- Read user's description. Classify: bug vs feature/enhancement vs question. If ambiguous, ask once.
- Check repo:
gh repo view --json nameWithOwner,hasIssuesEnabled. If issues disabled, stop. - List existing issue templates:
gh issue create --helpnotes--template. Check.github/ISSUE_TEMPLATE/— if templates exist, prefer--template <file>and let user fill in via editor. Otherwise build body inline. - Search for duplicates:
gh issue list --search "<key terms>" --state all --limit 5. If close match exists, surface URL + ask before opening new. - Draft title — imperative for features (
Add X), declarative for bugs (X crashes when Y). ≤70 chars. No "Bug:" / "Feature:" prefix unless repo convention demands. - Draft body per shape below (HEREDOC). Atomic tone — drop filler, exact symbols in backticks, no hedging, no AI bylines. Redact per the Privacy section as you draft — never write raw PII, secrets, or third-party identifiers into the body.
- Map classification → label:
bug→bug,feature/enhancement→enhancement,question→question. Verify the label exists on the repo first:gh label list --search <name>. Skip the label if it doesn't exist (don't auto-create). User-specified labels stack on top. - Preview: print the full rendered issue — title, body, target repo, labels — and get an explicit go-ahead from the user before creating. See Privacy.
gh issue create --title "<title>" --body "$(cat <<'EOF' … EOF)" [--label <classified>] [--label <user-specified>].- Print issue URL.
{{ template "report-issue-privacy" . }}
Body shapes
Bug
## Summary
<one-line statement of what's broken>
## Repro
1. <step>
2. <step>
3. <step>
## Expected
<what should happen>
## Actual
<what happens, including exact error message in a code block>
## Environment
- Version / commit: <x>
- OS: <x>
- Runtime: <x>
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 · 102 lines · 22 tokens per session scan A 04e14ee028c4
report-issue is a command published in the GitHub repository damusix/atomic-claude (113 stars, last pushed 10d ago), licensed MIT. It adds 22 tokens to every session and 776 once invoked, about $0.0001 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.
status
Show current Heimdall state — project phase, active agents, quality gates, conflicts.
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
handoff
Write a session handoff document for continuity.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
asana-setup
Set up the Asana V2 MCP server connection (one-time OAuth app + fuxi mcp add).