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 dev-workflowsWrote 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/agents/ihudak/ihudak-claude-plugins/doc-planner)<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/doc-planner"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/doc-planner.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 5.1 | $0.00076 | $0.05856 |
| Opus 5 | $0.00038 | $0.02928 |
| Sonnet 5 | $0.00015 | $0.01171 |
| Haiku 4.5 | $0.00008 | $0.00586 |
Grade A, and why
doc-planner 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 today.
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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesise the documentation checklist that /document Phase 6.3 follows and /document Phase 7 (doc-reviewer) checks against.
Not a writer — this agent plans; the main command writes.
Inputs
folder_read: <the YAML the orchestrator assembled by reading the resolved folder — the PRD frontmatter and body, the Epic set, and the artifacts present; the orchestrator names its keys in the dispatch, since no schema file defines them>
diff_summaries: <array of diff-summarizer outputs; one entry per repo>
write_targets: <confirmed list from doc-location-finder + user; each has kind, section, path, rationale>
screenshots: [<array of user-provided absolute image paths; possibly empty>]
screenshot_staging_dir: <absolute dir the command resolved for cdn_upload_required staging — a persistent directory the operator named, never inside a repo; null when no screenshots were provided>
code_repos: <array of {slug, path} for source-truth verification; the clones resolved for diff-summarizer; [] when unavailable>
specs_dir: <absolute path to the PRD's spec folder (PRODUCT-NNNN*), or null; the authoritative intended-behavior source>
repo_root: <absolute path to the docs repo root>
profile: <the resolved docs-profile (built-in example-docs default, in-repo, or generated); supplies spaces[], tokens, internal_links>
Refuse to run without folder_read, write_targets, and repo_root. folder_read is assembled by the orchestrator from the resolved folder — it is not an agent's return value, and no schema file defines it; the dispatch names its keys.
Process
First — read the repo's own authoring guidance (once, not per target). Scan repo_root (and .claude/) for whichever of these exist: CONTRIBUTING.md, CONTRIBUTION.md, README.md, CLAUDE.md, STYLE.md, DOCUMENTATION-GUIDELINES.md. Extract the authoring / structural rules a writer must follow — required page sections, voice/tone directives, page templates, structure and naming conventions, prohibited constructs. Distil them into the repo_authoring_guidance output block (one bullet per rule, each tagged with its source file). Ignore purely operational content (build/setup steps, PR and branch mechanics — branch naming is handled by the command, not here). These rules augment, never override the built-in example-docs references and the prose-style checks; when a repo rule conflicts with those, note it rather than silently overriding. Factor the extracted rules into the topic and section planning below. Emit repo_authoring_guidance: [] when no guidance files exist or none carry authoring rules.
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.
- today Changed · +1 tokens per session 0476cc1fceab
- 5d ago First seen · 197 lines · 75 tokens per session scan A f02187a35d97
doc-planner is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 5,856 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 agents, from other repositories
code-reviewer
Reviews all changed files in a change set in an isolated context and returns structured findings as JSON. Spawned by the /review-gate:review orchestrator. Not for general questions.
code-filter
Independent falsify pass for review-gate findings. Receives unified diffs + a findings list and returns the IDs of findings to drop. Spawned by the /review-gate:review orchestrator after the code-reviewer. Not for general questions.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.
Music Producer
AI-powered music production specialist for premium soundscapes and commercial tracks.
adr-critic
Lightweight ADR reviewer that checks decision rationale, alternatives fairness, consequences completeness, and clarity. Reads Author's Notes as prioritized attack vectors. Use when the ADR review operation needs a quick quality check.