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/documentgit 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/document)<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/document"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/document.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 | $0.00084 | $0.34428 |
| Opus 5 | $0.00042 | $0.17214 |
| Sonnet 5 | $0.00017 | $0.06886 |
| Haiku 4.5 | $0.00008 | $0.03443 |
Grade A, and why
document 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 3d 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 — 1,629 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate product documentation for the Jira Product Requirements Document: $ARGUMENTS
Signature: PRODUCT-NNNN — the Jira Product Requirements Document key, and nothing else. Phase 5.5 resolves each write target against the content roots the resolved profile declares, and Phase 6.3 writes each page into the root that owns it.
/document (Jira mode) is the Jira-driven feature-documentation workflow. Given a Jira Product Requirements Document key, it reads the full Jira hierarchy from pre-exported markdown in the user's Obsidian vault, resolves PR URLs to local git repos, runs parallel PR-diff summaries, synthesises product documentation, runs style-check + Opus review gates, and writes the output to the current working directory (a product docs repository).
For small one-off doc edits, use direct mode (below). For writing child Epic drafts from a PRD, use /epics. For release notes, use /release-notes — this command never writes release-notes / what's-new pages, because those are generated from Jira by the docs team's automation.
Mode detection
/document has two modes, selected by the first argument token:
- Jira mode (Mode A) — the input resolves
jira-drivenvia the shared front-end (${CLAUDE_PLUGIN_ROOT}/references/jira-input-resolution.md): a first token matching a JiraID (^[A-Z][A-Z0-9]+-[0-9]+), or a directory that inspects as a Jira-export (contains<KEY>-index.md). The front-end's Fallback B handles a JiraID-shaped token with nojira-products/<KEY>folder. - Direct mode (Mode B) — the input resolves
direct(a leading@filetoken, free-text prose, or a non-Jira-export directory, which Mode B handles via its existing "anything else" path).
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 the code/docs repo this run is working
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 for the whole
run — the terminal commit-artifacts step skips on it.
Echo the detected mode, then proceed to that mode's phases. The two modes share the same docs-style-checker / doc-fixer agents; only Jira mode also runs doc-reviewer (each mode emits its own final report).
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.
- 3d ago First seen · 1,629 lines · 84 tokens per session scan A 75395bcc20a4
document is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 34,428 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.
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.
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.
add-skill
Add a new Skill to the current plugin with proper structure.