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/backpropnpx skills add raisedadead/claude-code-plugins --skill backpropgit 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 | $0.00071 | $0.02882 |
| Opus 5 | $0.00036 | $0.01441 |
| Sonnet 5 | $0.00014 | $0.00576 |
| Haiku 4.5 | $0.00007 | $0.00288 |
Grade A, and why
backprop 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ds:backprop — bug → invariant protocol
Six steps. Append-only on §B + §V. Resumable.
Inputs
<B-id>(e.g.B5): existing bug row, resume / amend.<bug-description>free text: new bug, scaffold a §B row from it.--resume: explicit override of the auto-detected resume point.
Steps
0. Detect host env
Per ADAPTERS.md. Note HAS_CAVEMEM (recurrence research benefits).
DOSSIER.md writes go through the bundled helpers (FORMAT.md §15): $CLAUDE_PLUGIN_ROOT/hooks/lib-row-flip.sh <dir> <id> <state> [cite] flips a §T state cell, $CLAUDE_PLUGIN_ROOT/hooks/lib-s-append.sh <dir> "<event>" appends §S. The §S code-fences below show the full line — pass only the text after the timestamp, which the script prepends.
There is no row-flip for §B. lib-row-flip.sh <dir> B<N> <state> exits 1 printing lib-row-flip: refuses Bugs rows (no state column — would destroy cells); use ds:backprop — §B carries id | bug | root cause | invariant added | fix cite and no state column at all (FORMAT.md §9, §15). Every §B mutation in this skill is therefore an atomic whole-file write: the row append in step 6, the invariant added update in step 7, the fix cite update in step 8.
1. Locate live dossier
Per ds:status step 1. Refuse when there is none.
2. Acquire lock
Write <dir>/.ds-lock with skill: "ds:backprop", target: "B<N-or-pending>".
3. Resume detection
Read §S, grep ds:backprop <target>:
| Last event | Resume point |
|---|---|
| (none) | full run from step 4 |
START |
step 4 (re-scope) |
flake=<rate> |
1.0 → step 5; 0.0 → step 4 (re-scope); 0<r<1 → write closed §B row (step 4.5 flaky branch) then step 9 |
test=<sha> |
step 6 |
§B=B<N> |
step 7 (invariant decision) |
§V=V<N> |
step 8 (fix) |
fix=<sha> |
step 9 (close) |
DONE |
exit |
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 · 224 lines · 71 tokens per session scan A 7956f8c6b932
backprop is a skill published in the GitHub repository raisedadead/claude-code-plugins (2 stars, last pushed 6d ago), licensed ISC. It adds 71 tokens to every session and 2,882 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…