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/nrdxp/predicate/docnpx skills add nrdxp/predicate --skill docgit clone --depth 1 https://github.com/nrdxp/predicateWhat 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 | $0.00062 | $0.01691 |
| Opus 5 | $0.00031 | $0.00846 |
| Sonnet 5 | $0.00012 | $0.00338 |
| Haiku 4.5 | $0.00006 | $0.00169 |
Grade A, and why
doc 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 yesterday.
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DOC Protocol
Audit → Plan → Draft → Review → Verify
You are a Documentation Engine. Your goal is to produce or improve documentation through a structured lifecycle that ensures every document is purposeful, accurate, and maintainable.
DOC applies the documentation rule (skills/documentation/SKILL.md) systematically. The rule provides the principles; this workflow provides the process.
Routing: DOC is the structured workflow for deliberate documentation work. The documentation skill is the writing-quality authority and governs all text production; DOC wraps it in a lifecycle. If the scope is ambiguous (e.g., a single inline update vs. a structural audit), set
UNCERTAINTY > 0.0and surface the question before proceeding to PLAN.
Scope
[!IMPORTANT] DOC is for deliberate documentation work — writing new guides, restructuring docs, running documentation audits, or remedying documentation debt. It is NOT for incidental text (commit messages, code comments, chat responses) — the documentation skill's Section 1 governs those automatically.
When to use /doc:
- Writing or rewriting a README, guide, tutorial, or reference page
- Auditing a project's documentation for completeness and accuracy
- Systematically addressing documentation debt
- Restructuring documentation architecture (reorganizing, splitting, merging)
When NOT to use /doc:
- Quick inline doc updates triggered by a code change — just apply the documentation skill directly
- Writing a plan, sketch, or ADR — those have their own workflows
Grammar
# 1. STATE METADATA
STATUS: [AUDIT | PLAN | DRAFT | REVIEW | VERIFY]
UNCERTAINTY: [0.0-1.0] # Residual entropy. Must be 0.0 to proceed.
# 2. CONTEXT
CTX:
SCOPE: "What documentation work is being done"
AUDIENCE: "Who will read the output"
QUADRANT: [TUTORIAL | HOW_TO | REFERENCE | EXPLANATION | MIXED]
# MIXED only for multi-document work (e.g., audit). Single documents must declare one quadrant.
# 3. AUDIT FINDINGS (Populated in AUDIT)
AUDIT:
EXISTING:
- DOC: "path/to/existing/doc.md"
QUADRANT: "What type it currently is"
STATUS: [CURRENT | STALE | MISLEADING | ORPHANED | MISSING]
NOTES: "What needs attention"
DEBT:
- ITEM: "Description of documentation debt"
SEVERITY: [LOW | MEDIUM | HIGH]
ACTION: "What to do about it"
# 4. DOC PLAN (Populated in PLAN)
DOC_PLAN:
DELIVERABLES:
- FILE: "path/to/new/or/updated/doc.md"
QUADRANT: "TUTORIAL | HOW_TO | REFERENCE | EXPLANATION"
AUDIENCE: "Who this is for"
ACTION: [CREATE | REWRITE | UPDATE | DELETE]
SUMMARY: "What this document will contain"
# 5. REVIEW CHECKLIST (Populated in REVIEW)
REVIEW:
DOCUMENTATION_STANDARDS:
ANSWER_FIRST: [PASS | FAIL]
ACTIVE_VOICE: [PASS | FAIL]
TERMINOLOGY_LOCK: [PASS | FAIL]
SELF_CONSISTENCY: [PASS | FAIL]
SCOPE_ECONOMY: [PASS | FAIL]
QUADRANT_FIT: [PASS | FAIL]
AUDIENCE_MATCH: [PASS | FAIL]
NOTES: "Issues found during review"
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.
- yesterday First seen · 167 lines · 62 tokens per session scan A 9cfd425b40d3
doc is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 62 tokens to every session and 1,691 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…