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/chroniclenpx skills add nrdxp/predicate --skill chroniclegit 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 | $0.00070 | $0.00733 |
| Opus 5 | $0.00035 | $0.00367 |
| Sonnet 5 | $0.00014 | $0.00147 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
chronicle 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 2d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chronicle Workflow
A structured approach to maintaining a high-level, conceptual project chronicle (docs/chronicle.md). This chronicle serves as a persistent decision record, mapping the evolution of the codebase's architecture, workflows, and conventions to optimize agent context and human understanding.
Purpose
Standard git logs are either too detailed or too fragmented to provide deep architectural context. The Chronicle Workflow maintains an incremental, high-level chronicle file in the repository. Because it uses a commit cutoff marker in its frontmatter, it can be updated cheaply and incrementally over time, serving as a durable project history journal.
Execution Protocol
To update or initialize the chronicle, follow these steps:
1. Prepare Pending Logs
Run the helper script in prepare mode:
python3 skills/chronicle/scripts/update_chronicle.py --prepare
If the chronicle is already up to date, the script will output:
Chronicle is already up to date with HEAD. and you may exit.
Otherwise, it will output a batch of up to 50 commits (from oldest to newest) along with changed files. Note the TARGET_END_SHA printed at the end of the output — you pass it back to the write step so the recorded range is bound to exactly the commits you summarized (immune to HEAD moving in between).
2. Group and Summarize
Using your LLM reasoning, analyze the batch output. Group the commits into conceptual themes rather than listing them raw. Focus on why changes were made, what design decisions were reached, and major milestones.
Organize the summary into the following categories where relevant:
- Architectural Shift / Design Decisions: Major structural changes, folder reorganizations, and key trade-offs.
- Workflow & Rulesets: Updates to workflows, rulesets, and agent configurations.
- Features & Implementation: Core user-facing features and implementations.
- Infrastructure & Quality: CI, tooling, linting, and test configurations.
- Documentation: Significant documentation changes (beyond minor typos).
What ships with it
1 file 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.
- 2d ago First seen · 68 lines · 70 tokens per session scan A add733f658a6
chronicle is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 70 tokens to every session and 733 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…