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 skills/alexpialetski/doccraft/doccraft-queue-auditnpx skills add alexpialetski/doccraft --skill doccraft-queue-auditgit clone --depth 1 https://github.com/alexpialetski/doccraftWrote 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/skills/alexpialetski/doccraft/doccraft-queue-audit)<a href="https://agentmods.dev/skills/alexpialetski/doccraft/doccraft-queue-audit"><img src="https://agentmods.dev/badge/skills/alexpialetski/doccraft/doccraft-queue-audit.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 | $0.00161 | $0.05301 |
| Opus 5 | $0.00081 | $0.02651 |
| Sonnet 5 | $0.00032 | $0.01060 |
| Haiku 4.5 | $0.00016 | $0.00530 |
Grade A, and why
doccraft-queue-audit 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 — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managed by doccraft —
doccraft updateregenerates this file. Local edits will be overwritten. Seedoccraft.jsonto override project-specific vocabulary and paths without touching this file.
doccraft — queue, dependency audit, and parallel waves
When to use
- After adding a story, changing
depends_on/id, or reshuffling priorities and you want a sanity check ondocs/queue.md. - The user asks "what can I work on next", "what's unblocked", "sanity-check the queue", or similar pick-next / dependency questions.
- The user asks for parallel-ready batches ("what can I run in parallel?") — see Parallel waves below.
- The user pastes the suggested follow-up block from
doccraft-story.
Not for: authoring a new story (use doccraft-story), recording a
decision (use doccraft-adr), proposing artifacts from a chat thread
(use doccraft-session-wrap), or closing one specific story end-to-end
(use doccraft-close — it does the status/backlog/queue/epic transition,
then defers to this skill's reconcile invariants).
Configuration
Read doccraft.yaml at invocation. Every key below has a default in the
rest of this body so a missing config file is a soft fallback, not an error.
Relevant keys:
docsDir— root folder for all docs. Default:docs. Stories, queue, and backlog are at{docsDir}/stories/,{docsDir}/queue.md,{docsDir}/backlog.md.queue.tables.suggestedOrder,queue.tables.platformSpikes— the heading text this skill uses to find the two tables in the queue file. Defaults:Suggested order,Platform spikes. Rename in config if the project uses different headings; the skill matches on heading text, not row position.story.id.pattern— regex for valid story ids. Used when listing unknown-id errors and when normalising obvious typos.queueAudit.laneFrom— tag-prefix priority list for the lane heuristic in the parallel-waves pass. Default:[area, slice]. Set to[slice, area]for projects that group work primarily by product surface. May also includeepic— when present (and an epics extension defines theepic:story field), the queue groups by epic, which is the primary ordering for milestone/epic projects (ADR 016).story.status— the project's allowed status values. Whichever of these mean "no longer active work" are terminal (donealways, plus any the project adds:done-no-promote,abandoned,absorbed). Wherever this skill says a story isdone/ shipped, it means any terminal status — read the vocabulary rather than matching the literaldone, or a story closed asabsorbedwill wrongly look unfinished and never satisfy its dependents.queueAudit.scale.maxStoryFiles,queueAudit.scale.maxQueueReorderPct— thresholds that trigger stop-and-confirm in Agent mode. Defaults:5,50. See Containment below.
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 · 461 lines · 161 tokens per session scan A c69f02ec2b92
doccraft-queue-audit is a skill published in the GitHub repository alexpialetski/doccraft (4 stars, last pushed 2mo ago), licensed MIT. It adds 161 tokens to every session and 5,301 once invoked, about $0.0008 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 skills, from other repositories
retro
CP-7 retrospective: audit checkpoints, evidence quality, action items, and harvest candidates. Closes the V-model cycle and feeds the next run. Use via /retro after ship, escalate, or significant session.
pad
Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.
pm-init
Skill "pm-init" from wei63w/pm-manager, covering user input, outline, 1. scaffold, 2. lifecycle and type and 3. detect spec kit (required).
fde
Keeps the engagement record for client work. Use when they name a client or stakeholder. Use when they debrief a meeting or paste notes. Use when they ask what was agreed. Use when they run a POC, change the client's codebase, prove it on their staging, go live, or need evals before a model acts. Use when they prep a…
pm-arch
Skill "pm-arch" from wei63w/pm-manager, covering user input, outline, done when and shared workflow (all /pm- commands).
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).