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/juxt/claude-plugins/sitrepnpx skills add juxt/claude-plugins --skill sitrepgit clone --depth 1 https://github.com/juxt/claude-pluginsWhat 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 | $0.00089 | $0.01446 |
| Opus 5 | $0.00044 | $0.00723 |
| Sonnet 5 | $0.00018 | $0.00289 |
| Haiku 4.5 | $0.00009 | $0.00145 |
Grade A, and why
sitrep 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chalk Sitrep — Where the Session Has Got To
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
A sitrep is written for whoever picks the session up next — the user after a break, a future agent after a compaction, or the user's colleague reading over their shoulder. It is not a log of the session. It is the state the session has reached, and what still needs a decision.
$ARGUMENTS, if given, narrows the scope; report only on that and say in one line what you left out.
Before you write
- Load
chalk:mindmap— every parent a claim its children back up, and the typed-ID scheme the Open section runs on. chalk:voice's register applies, its palette doesn't. A sitrep is a terminal reply, not a GitHub artefact: no sections drawn from the palette, and no self-ranking, no smoke, no mea culpas.
Ground the report before writing it
A sitrep that trusts the transcript reports intentions as achievements. The transcript records what was attempted; the repo records what happened.
-
Check the working tree —
git status,git diff --stat, andgit logback to where the session started. This is what settles the Done/Open boundary for anything touching code. -
Re-read the artefacts the session claims to have produced where cheap — the file, the issue, the PR body. A file written three edits ago may not say what the session thinks it says.
-
Say so if the context was compacted. One line, at the top: the earlier part of the session is a summary, so coverage before that point is partial. The reader needs to know which half of the report is first-hand.
Section 1: Done
One bullet per change that actually landed, children carrying the specifics. No IDs here — Done is not up for reply, and IDs on it are noise.
- Landed means verified, not attempted: the file is written, the test passed, the commit exists.
- Tag anything claimed but unchecked with
unverified:rather than promoting or dropping it. A test that was written but never run is a real result and a real caveat; both belong on the line. - Something discussed but not built is not Done — it is an idea, and belongs in Open.
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 · 100 lines · 89 tokens per session scan A 74bd5b1b1c23
sitrep is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 1,446 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 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…