Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ihudak/ihudak-claude-plugins/plugin install workflows-coreWrote 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/prompt-grill-me)<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/prompt-grill-me"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/prompt-grill-me/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/ihudak/ihudak-claude-plugins/prompt-grill-me"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/prompt-grill-me.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 | $0.00048 | $0.01462 |
| Opus 5.5 | $0.00019 | $0.00585 |
| Sonnet 5.5 | $0.00010 | $0.00292 |
| Haiku 4.5 | $0.00005 | $0.00146 |
Grade A, and why
prompt-grill-me 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 23d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Log a corrective interaction, then grill the fix: $ARGUMENTS
/prompt-grill-me is for when a command of this plugin family produced something wrong
and you want a bounded one-question-at-a-time interrogation (≤5 questions) of
the correction. It captures the corrective triple as plugin feedback, then
grills the fix inline following the embedded grilling technique
(${CLAUDE_PLUGIN_ROOT}/references/grilling-technique.md). origin: prompt.
The interrogation is self-contained — this command owns the grill and has no plugin dependency.
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 — Identify the target
Infer the target command from recent context — which command's output you are
correcting. Ask only if genuinely ambiguous (one grouped prompt of 2–4 options; the
harness supplies the free-text escape). If no command applies, use n/a.
Phase 2 — Persist the corrective triple
Cite ${CLAUDE_PLUGIN_ROOT}/references/feedback-emission.md and call its
emit-prompt entry point (§6). Provide:
- Friction — what the command produced that was wrong.
- User prompt —
$ARGUMENTS, verbatim (never paraphrased). - Resolution —
Grilled the fix inline. command(Phase 1), an inferredcategory(§1 vocab, reuse-first),impact,key(ornull),source.
emit-prompt resolves the write target via the §2 specs-first ladder, formats
the entry with the two extra prose blocks (origin: prompt), appends per §3
(never silently skipped), and writes silently. Surface the persisted path.
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.
- 23d ago Changed 5952ea88e95c
- 28d ago Changed 3ecb4876710b
- 1mo ago Changed · +5 lines 5601b309bdb5
- 1mo ago First seen · 104 lines · 48 tokens per session scan A 46ce528ba380
prompt-grill-me is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 24d ago), licensed MIT. It adds 48 tokens to every session and 1,462 once invoked, about $0.0002 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 2026-09-05.
Other commands, from other repositories
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact. Scope it to a release's changes with a git range ( .. ) or changes for the uncommitted working tree; audit the whole repository for the first…
cloudflare-durable-objects:debug
Interactive Durable Objects debugging workflow. Diagnoses common DO errors, configuration issues, and runtime problems with step-by-step troubleshooting.
cloudflare-durable-objects:optimize
Interactive Durable Objects performance optimization assistant. Analyzes existing DO code and provides specific optimization recommendations with implementation guidance.
cloudflare-durable-objects:migrate
Interactive Durable Objects migration assistant. Guides through new class creation, renaming, deletion, and transfer migrations with validation.
cloudflare-queues:troubleshoot
Quick troubleshooting for common Cloudflare Queues issues.
cloudflare-workers:debug
Interactive debugging workflow for Cloudflare Workers. Diagnoses deployment errors, runtime issues, and performance problems with step-by-step fixes.