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.
npx agentmods add commands/randomittin/heimdall/feedbackgit clone --depth 1 https://github.com/randomittin/heimdallWhat 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 | $0.00102 | $0.00884 |
| Opus 5 | $0.00051 | $0.00442 |
| Sonnet 5 | $0.00020 | $0.00177 |
| Haiku 4.5 | $0.00010 | $0.00088 |
Grade A, and why
feedback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hmd:feedback — File Team Feedback as a GitHub Issue
Use when a team dev wants to send feedback (friction, a request, a note on the team flow). It raises a GitHub issue on the repo carrying the dev's words plus a tiny context footer — nothing from the session, the codebase, or the environment.
Process
-
Take the dev's message verbatim. Their words are the feedback. Do NOT paraphrase, expand with session details, or attach transcript/code. If the message is empty, ask once for it; otherwise proceed.
-
Run the CLI — it does the work (connector auth, secret-scan, labeling):
"${CLAUDE_PLUGIN_ROOT}/bin/heimdall-feedback" "<the dev's message>"Optional minimal context (only if obviously relevant — never invent it):
"${CLAUDE_PLUGIN_ROOT}/bin/heimdall-feedback" "<message>" \ --command "<hmd command in play>" --phase "<phase in play>"The CLI reuses the issue-loop's GitHub plumbing (
bin/lib/issue_config.pyfor config + credential resolution andbin/lib/connectors/github.pyfor the POST). It auto-applies thefeedbackandfrom-hmdlabels and appends only the hmd version (fromplugin.json) plus any--command/--phaseyou pass. -
Relay the result. On success the CLI prints
filed as issue #Nand the URL on the next line — pass both to the dev as one line:Filed: <URL>. -
On failure, surface the exact error (don't retry blindly):
- exit 1
github connector is not configured→ the repo's.heimdall/issue-loop.config.jsonneeds aconnectors.githubblock (repo+token_env); see.heimdall/issue-loop.config.json.example. - exit 1
no credential→ the namedtoken_envenv var isn't exported. - exit 5
refused — ... credential→ the message contained a secret shape; tell the dev to strip the secret and resubmit. Do NOT work around this.
- exit 1
Constraints
- No-secret discipline. Feedback is the dev's words ONLY. Never include session content, code snippets, file paths, stack traces, or secrets in the message. The CLI scans for credential shapes and refuses if it finds one — treat that refusal as correct, never bypass it.
- Files against the repo's issue tracker (the
connectors.github.repofrom the issue-loop config) — not necessarily the plugin repo. For bugs in Heimdall itself, use/hmd:report-buginstead. - The CLI is mockable:
--dry-runprints the JSON payload (title/body/labels) without filing — used bytest/feedback.test.sh.
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.
- yesterday First seen · 69 lines · 102 tokens per session scan A 2160234c14e1
feedback is a command published in the GitHub repository randomittin/heimdall (5 stars, last pushed 11d ago), licensed MIT. It adds 102 tokens to every session and 884 once invoked, about $0.0005 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.
Other commands, from other repositories
autocode
Fully autonomous development pipeline. Give it a feature description or PRD file and it will plan, write tests, implement code, run tests, and verify — all automatically with zero human intervention.
autocode-new
Scan current project and generate a project-specific autocode development pipeline (agents, commands, rules, hooks). Interactive setup wizard.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
dev-planner
Generate or update DEV-PLAN.md with phased development plan from Product-Spec.md.
iterate
Iteration delivery — delivery check + archive + commit & tag + bump version.