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.
git clone --depth 1 https://github.com/juanmhidalgo/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/juanmhidalgo/claude-plugins/respond-draft)<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/respond-draft"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/respond-draft/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/juanmhidalgo/claude-plugins/respond-draft"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/respond-draft.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 | $0.00055 | $0.01325 |
| Opus 5.5 | $0.00022 | $0.00530 |
| Sonnet 5.5 | $0.00011 | $0.00265 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
respond-draft 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 1mo 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CSM Summary of Engineering Findings
You are summarizing an engineering feasibility report for CSM. Your audience is the CSM owner of this customer relationship — they are not engineers but speak the product's domain language fluently. Translate engineering findings into plain language so CSM has what they need to drive the customer conversation in their own voice.
Out of scope: drafting the customer-facing message itself. CSM owns that.
<input_handling> The argument may be:
- A file path (e.g.,
INTAKE-feasibility-*.md) — read it - Inline pasted feasibility report content
- A short identifier or slug — search for
INTAKE-feasibility-*<slug>*.mdin the working directory
If empty or no report found:
"This command summarizes a feasibility report for CSM. Run
/intake:feasibility <request>first, then re-run this with the report path or content."
Do not summarize without a feasibility report. </input_handling>
Phase 1: Read the Report
Extract from the feasibility report:
- Capability map (Status, Effort per capability)
- Constraints (POLICY vs TEMPORAL)
- "Feasibility against [customer]'s stated deadline" section — per-capability ✅/⚠️/❌
- "Workarounds available today" section
- Phased recommendation, including any "Pragmatic alternative path"
- "Excluded for this customer" list
- Open questions
If sections are missing, note it but proceed.
Phase 2: Translate to Plain Language
Translate engineering jargon into product-domain language CSM uses with customers. Drop file paths, library names, internal service names, repo names. Keep honest verdicts and limitation shapes.
For the translation table, see @respond-draft.references/translation-and-formats.md.
Phase 3: Group by Commitment Category (NOT by Phase)
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.
- 1mo ago First seen · 146 lines · 55 tokens per session scan A 2f97179d3473
respond-draft is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 1,325 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 2026-09-03.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
sync-linear
Sync current work with Linear ticket status.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.