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/recordnpx skills add nrdxp/predicate --skill recordgit 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 | $0.00174 | $0.02880 |
| Opus 5 | $0.00087 | $0.01440 |
| Sonnet 5 | $0.00035 | $0.00576 |
| Haiku 4.5 | $0.00017 | $0.00288 |
Grade A, and why
record 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record — Durable Categorized Records
Ambient — applies to every predicate-enabled walk, not campaign-only.
The RECORD primitive manages durable artifacts across three complementary
substrates. What distinguishes it from generic note-taking is the
category model: each category of durable artifact has a defined
contract (machine-checkable shape), a .ledger home, and a trigger
(when to record into it).
Category model
Who holds the pen. One writer per node-kind-and-namespace, whoever it
is (the pen law — docs/entries.md): testimony
is signed by the walker who witnessed it and committed by that walker,
append-only, into .ledger/deposits/<topic>/<signer>/; synthesis,
decision, and narrative nodes — and every promotion — are the composer's.
In a solo predicate walk there is no composer: the walker signs
everything and executes this skill directly. Two writers interleaving one
namespace is how a zettelkasten becomes a shoebox.
Each category = {contract, .ledger home, trigger}. Categories are extensible: adding a fourth later is cheap — add the contract, home, and trigger row.
| category | contract | .ledger home | trigger |
|---|---|---|---|
| flight-log | narrative; no formal contract | .ledger/log/ |
at every significant step: decision, pivot, finding |
| tech-debt | skills/record/tech_debt.ncl |
.ledger/tech-debt/ |
when a limitation is accepted rather than fixed |
| process-feedback | skills/record/process_feedback.ncl |
.ledger/process-feedback/ |
when friction, a miss, an improvement, or a live process amendment is identified |
The flight-log category (existing)
Narrative zettelkasten — linked, curated trail of how the space was explored: decisions, pivots, adjustments. NOT exhaustive; navigable graph. See Recording (continuous) and Promotion for the full flight-log model.
The tech-debt category (new)
A first-class, machine-shaped entry for a known limitation or deferred decision — absorbs the campaign's "accepted limitations / tail" so they are trackable and actionable rather than buried in prose log entries.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 282 lines · 174 tokens per session scan A 3dca9551056e
record is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 174 tokens to every session and 2,880 once invoked, about $0.0009 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…