report-issue-with-atomic

report-issue-with-atomic is a command for coding agents from damusix/atomic-claude. It costs 27 tokens per session (1,246 once invoked), scanned A, original, MIT.

A command for opening a bug report or feature request against the atomic-claude project, the system that provides these commands and skills. It is meant for problems in that system, not in the project you are currently coding.

In plain words
What is it for?
Use it when an installed atomic-claude command, skill, agent, or configuration behaves incorrectly or needs a change.
Why use it?
It prevents issues from being sent to the wrong repository. The report is submitted by the user rather than created automatically.

Command

Install

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.

agentmods
npx agentmods add commands/damusix/atomic-claude/report-issue-with-atomic
Clone the repo
git clone --depth 1 https://github.com/damusix/atomic-claude

Wrote 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.

agentmods badge for report-issue-with-atomic

README.md
[![agentmods](https://agentmods.dev/badge/commands/damusix/atomic-claude/report-issue-with-atomic.svg)](https://agentmods.dev/commands/damusix/atomic-claude/report-issue-with-atomic)
Your own site
<a href="https://agentmods.dev/commands/damusix/atomic-claude/report-issue-with-atomic"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/report-issue-with-atomic.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,246 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.01246
Opus 5 $0.00014 $0.00623
Sonnet 5 $0.00005 $0.00249
Haiku 4.5 $0.00003 $0.00125

Measured 5d ago against content hash ed1633df321a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

report-issue-with-atomic scanned grade A 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Install method: <curl install.sh | brew | source | docker>
context/commands/report-issue-with-atomic.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope

This command files an issue against atomic-claude (damusix/atomic-claude) — the system that installs commands, skills, agents, and the output style into ~/.claude/. Use it when the problem is with atomic-claude's behavior, not the user's current repo. For issues in the user's current project, use /report-issue instead.

Hardcoded target: damusix/atomic-claude. Do not infer the target from gh repo view or cwd — the user is almost always inside a different repo when invoking this.

Invoked from /retrospective-learning. The retrospective audit routes its atomic-meta tier (finding tier 3 — frustration positionally co-located with an atomic artifact in the session) to this command. When the user opts "Open issue" on a meta finding, the audit prints the runnable /report-issue-with-atomic <one-line summary> and lets the user invoke it themselves with the surrounding context. Auto-invocation is forbidden — per axiom 3, issue creation is a public action and the user submits the body. See commands/retrospective-learning.md for the upstream contract.

Prereqs

  • command -v gh — if missing: tell user to install (brew install gh / winget install --id GitHub.cli / https://cli.github.com/) then gh auth login. Stop.
  • gh auth status — if unauthed: tell user gh auth login. Stop.

Steps

  1. Read user's description. Classify: bug vs feature/enhancement vs question. If ambiguous, ask once.
  2. Confirm target with one sentence: "Filing against damusix/atomic-claude (not your current repo)." Proceed unless user objects.
  3. Capture installed version: run atomic --version if the binary is on PATH. Include in body. If missing, note "atomic binary not found on PATH".
  4. Search for duplicates: gh issue list --repo damusix/atomic-claude --search "<key terms>" --state all --limit 5. If close match exists, surface URL + ask before opening new.
  5. Check repo templates: gh api repos/damusix/atomic-claude/contents/.github/ISSUE_TEMPLATE 2>/dev/null — if templates exist, prefer --template <file>. Otherwise build body inline.
  6. Draft title — imperative for features (Add X), declarative for bugs (/commit skips signals refresh on staged-only changes). ≤70 chars. No "Bug:" / "Feature:" prefix.
  7. 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. This target repo is public, so redaction is not optional.
  8. Map classification → label: bugbug, feature/enhancementenhancement, questionquestion. Verify the label exists on the target repo first: gh label list --repo damusix/atomic-claude --search <name>. Skip the label if it doesn't exist (don't auto-create). User-specified labels stack on top.
  9. Preview: print the full rendered issue — title, body, target repo, labels — and get an explicit go-ahead from the user before creating. See Privacy.
  10. gh issue create --repo damusix/atomic-claude --title "<title>" --body "$(cat <<'EOF' … EOF)" [--label <classified>] [--label <user-specified>].
  11. Print issue URL.

Read the full file on GitHub · 115 lines

Changes

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.

  1. 5d ago First seen · 115 lines · 27 tokens per session scan A ed1633df321a

Subscribe to this mod's changes

report-issue-with-atomic is a command published in the GitHub repository damusix/atomic-claude (84 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,246 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.