A command for filing a GitHub issue about the Heimdall plugin itself. It classifies the report and includes relevant environment details, reproduction steps, expected behavior, and actual behavior.

Use it to report a bug, feature request, documentation problem, enhancement, or question about Heimdall.

It turns an in-session report into a structured issue that maintainers can investigate. It also distinguishes plugin problems from problems in the project being worked on.

report-bug — Command by randomittin

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/randomittin/heimdall/report-bug

Clone the repo

git clone --depth 1 https://github.com/randomittin/heimdall

Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 961 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00084	$0.00961
Opus 5	$0.00042	$0.00481
Sonnet 5	$0.00017	$0.00192
Haiku 4.5	$0.00008	$0.00096

Measured 2d ago against content hash 1e34d9650393, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

report-bug 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 2d 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.

commands/report-bug.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/hmd:report-bug — File an Issue Against the Heimdall Plugin

Use when the user wants to report a bug, request a feature, or flag a docs problem in the Heimdall plugin itself (NOT in the project they're working on).

Process

Classify the report from the user's description:
- bug — something in Heimdall is broken or behaves wrong
- feature — a new capability they want
- docs — wrong/missing/confusing docs or help text
- question — they want clarification (last resort — try answering first)
- enhancement — improvement to existing behavior
If unclear, ask one clarifying question. Do NOT spam questions.
Gather details — pull from the conversation and (if relevant) recent tool output:
- What were they trying to do?
- What did Heimdall do instead?
- Reproduction steps (concrete commands or actions)
- Stack trace / error output (verbatim, in a fenced code block)
- Expected behavior

Compose the body as Markdown. Use this template:

## Summary
<one or two sentences>

## Steps to reproduce
1. ...
2. ...

## Expected behavior
<what should have happened>

## Actual behavior
<what did happen, with error output verbatim>

## Additional context
<any relevant details — only include if non-trivial>

Write the body to a temp file (e.g. /tmp/heimdall-issue-body-$$.md).

Compose a tight title — under 70 chars, imperative or descriptive. Examples:
- bug: parallelism-tracker fails on linux-musl (no fcntl.h)
- feature: add /hmd:rollback to revert last wave
- docs: agents/coder.md doesn't mention isolation: worktree
Invoke the helper:
```
"${CLAUDE_PLUGIN_ROOT}/bin/report-issue" \
  --title "<title>" \
  --body-file "/tmp/heimdall-issue-body-$$.md" \
  --kind <bug|feature|docs|question|enhancement>
```
The helper auto-prepends an ## Environment block with plugin SHA, OS, kernel, recent commits, and dirty cwd files. Do NOT duplicate that in your body — keep your body focused on the user's report.

Read the full file on GitHub · 96 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.

2d ago First seen · 96 lines · 84 tokens per session scan A 1e34d9650393

Subscribe to this mod's changes

report-bug is a command published in the GitHub repository randomittin/heimdall (5 stars, last pushed 11d ago), licensed MIT. It adds 84 tokens to every session and 961 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Code review Debugging Writing and docs ai-coding anthropic claude-code claude-plugin cli developer-tools

report-bug

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/hmd:report-bug — File an Issue Against the Heimdall Plugin

Process

What this file has done since we first saw it

Other commands, from other repositories

autocode

autocode-new

dispatcher

standup

dev-planner

iterate