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/raisedadead/claude-code-plugins/newnpx skills add raisedadead/claude-code-plugins --skill newgit clone --depth 1 https://github.com/raisedadead/claude-code-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 | $0.00046 | $0.02673 |
| Opus 5 | $0.00023 | $0.01337 |
| Sonnet 5 | $0.00009 | $0.00535 |
| Haiku 4.5 | $0.00005 | $0.00267 |
Grade A, and why
new scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ds:new — scaffold a new dossier
Creates .scratchpad/dossier/<YYYY-MM-DD>-<slug>/DOSSIER.md per FORMAT.md, then asks the operator for goal, scope and repos.
Inputs
<slug>from$ARGUMENTS(kebab-case, ≤30 chars). Empty → ask the operator.- Date defaults to today (
date +%Y-%m-%d). Override by prompt when migrating historical work.
Steps
0. Detect host env
Run once. Cache for the invocation.
command -v rtk &>/dev/null && echo HAS_RTK- check the tool namespace for
mcp__cavemem__*,mcp__fastedit__* - check available skills for
caveman:*,ck:*
See plugins/dossier/ADAPTERS.md for routing rules. An absent adapter is a skip.
The §S DONE line (step 6) appends via $CLAUDE_PLUGIN_ROOT/hooks/lib-s-append.sh <dir> "<event>" (FORMAT.md §15) — pass the text after the timestamp, which the script prepends. The initial scaffold is a full Write (new file).
1. Validate slug + path
- Slug matches
^[a-z0-9][a-z0-9-]{0,29}$. Anything else is refused with an explanation. - Compute
dir=.scratchpad/dossier/<date>-<slug>/. - Collision check:
direxists or.scratchpad/dossier/_archive/<date>-<slug>/exists (a same-day close+reopen) → ask the operator to bump to<slug>-2,<slug>-3, etc. Checking_archive/too avoids two INDEX rows keyed to one slug (Vm.1).
1.5. Grill gate (conditional)
Fires only when a grill artifact exists for this slug, so trivial ds:new runs are untouched. <slug> is the RESOLVED slug from step 1 (post-collision-bump; a bumped <slug>-2 starts without <slug>'s grill):
"$CLAUDE_PLUGIN_ROOT"/hooks/lib-assert-grill.sh .scratchpad "<slug>"
The helper discovers the newest .grill/<date>-<slug>.md by slug — grill's own date may be days older than today (multi-day --resume, pending-external waits) and the gate still finds it. Route on the exact exit code:
| exit | meaning | action |
|---|---|---|
| 0 | complete (path printed) | consume its ## Draft §G/§C in step 2 — do NOT re-ask; after the step-3 Write lands, stamp via lib-assert-grill.sh --consume .scratchpad "<slug>" "<date>-<slug>" (atomic tmp+mv per Vm.8; refuses a double-consume) |
| 1 | no artifact | proceed normally — grill is never required; step 2's clarify lever recommends it |
| 2, 3 | artifact incomplete / unconfirmed | REFUSE scaffold; point at ds:grill <slug> --resume (or delete the artifact to abandon) |
| 4 | artifact already consumed | proceed normally; recommend a fresh ds:grill <slug> — a consumed grill never feeds twice |
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 · 210 lines · 46 tokens per session scan A e86645bf86de
new is a skill published in the GitHub repository raisedadead/claude-code-plugins (2 stars, last pushed 6d ago), licensed ISC. It adds 46 tokens to every session and 2,673 once invoked, about $0.0002 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…