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/ihudak/ihudak-claude-plugins/feedbackgit clone --depth 1 https://github.com/ihudak/ihudak-claude-pluginsWrote 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/ihudak/ihudak-claude-plugins/feedback)<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/feedback"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/feedback.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.01512 |
| Opus 5 | $0.00027 | $0.00756 |
| Sonnet 5 | $0.00011 | $0.00302 |
| Haiku 4.5 | $0.00005 | $0.00151 |
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 4d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Log session feedback about the dev-workflows plugin: $ARGUMENTS
/feedback captures a manual note about the dev-workflows plugin itself —
friction you hit, or an improvement you want — and persists it per-PRD into the
specs repo so the plugin maintainer can aggregate feedback across engineers. It
is tied to no command and can be run any time. You author the prose; the
command fills the metadata and writes the entry. origin: manual.
This command captures signal about the plugin, not about your target
project. Target-project tooling advice does not belong here (see
${CLAUDE_PLUGIN_ROOT}/references/feedback-emission.md §4).
Phase 0 — Specs-repo preflight
Cite ${CLAUDE_PLUGIN_ROOT}/references/specs-repo-git.md and execute its
specs-preflight entry point (§3) inline: flush any leftover session
artifacts from an earlier run, retry an artifact commit that failed to push,
and settle the branch. This runs against $SPECS_PATH only — git -C "$SPECS_PATH", never a cd, so whatever repository you are standing in is
untouched (§1 rule 1). Prompt-free and silent when the specs repo is clean and
on its default branch. If a guard fires, emit its §5 notice; if it returns
specs_git: blocked (§3.3 G0), carry that flag — the terminal
commit-artifacts step skips on it.
Phase 1 — Compose the note
- If
$ARGUMENTSis empty, ask the user for the note (the friction and the improvement they want). Do not guess. - From the user's text, author two prose blocks — you may lightly tidy wording
but never invent content the user did not express:
- Friction — what about the plugin was wrong, slow, or missing.
- Suggested improvement — the change they want.
Phase 2 — Fill the metadata
Resolve, then confirm with the user in one grouped prompt (last choice always
"Other… (describe)"):
command— the exact slash-command name this note is about, inferred from recent context; orn/aif it is not about a specific command. Confirm.category— inferred from the controlled vocab in${CLAUDE_PLUGIN_ROOT}/references/feedback-emission.md§1 (missing-capability,wrong-output,ambiguous-prompt,missing-reference-doc,model-routing,manual-workaround,false-positive,docs-ux,other); reuse an existing value when it fits. Confirm.impact—blocker | friction | polish.author—git config user.emailrun in the specs repo (best-effort;unknownif unset).plugin_version— read from${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json.
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.
- 4d ago First seen · 112 lines · 54 tokens per session scan A 6f3b40b36e6a
feedback is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 5d ago), licensed MIT. It adds 54 tokens to every session and 1,512 once invoked, about $0.0003 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
doctor
Check that the review-gate push gate is actually wired up and able to run. Reports which adapters are active, whether the reviewer can be located, and any version skew between the plugin and the global git hook. Use when a push was not reviewed, when a gate error told you to run the doctor, or after installing or…
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.
cloudflare-r2:presigned-url
Generate presigned URLs for secure client-side uploads or downloads.
sheet-report
Analyze a Numbers or Excel file and generate a report with charts.
create_handoff
Create handoff document for transferring work to another session.
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.