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/convergenpx skills add raisedadead/claude-code-plugins --skill convergegit 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 | $0.00056 | $0.01336 |
| Opus 5 | $0.00028 | $0.00668 |
| Sonnet 5 | $0.00011 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
converge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ds:converge — ask the contract whether the wave is over
A §T list says what to do and never what done means, so the objective drifts to whatever was asked most recently. This verb reads the contract and answers from commands.
Run it
bash "${CLAUDE_PLUGIN_ROOT}"/hooks/lib-converge.sh [contract-path]
No argument → the runner resolves the live wave's contract: the tracked .dossier/ home first, then the wave directory's own CONTRACT.md. No live wave is PARSE — a closed wave's contract runs by explicit path only.
| exit | line | meaning |
|---|---|---|
| 0 | CONVERGE: MET <n>/<n> |
every criterion met — the wave is over |
| 1 | CONVERGE: UNMET <n> of <m> |
the named criteria are the remaining work |
| 2 | CONVERGE: PARSE — <why> |
the contract could not be read |
Read the CONVERGE: line before the exit code. A missing runner makes the interpreter exit 1 or 2 by itself, which are this tool's own UNMET and PARSE codes, so a number alone cannot separate a verdict from a crash. No CONVERGE: line means nothing ran.
Criteria are shell, and ds:close resolves a contract with no argument, so the runner names the work first: a contract: <path> header — carrying (wave-dir, untracked) when that home won — then one will run <id>. <command> line per criterion, flushed before the first command starts. The flush is load-bearing: every caller here reads a pipe, and a buffered block arrives at exit, after the commands it was meant to preview. In a repo somebody else wrote, read that block — the untracked home is a file no diff ever showed a reviewer.
What a contract looks like
.dossier/<date>-<slug>.md where the repo opted into tracking (the directory exists), else <wave-dir>/CONTRACT.md beside the ledger. The tracked home is the strong one: it can be cited as evidence and it outlives the wave's archive. ds:new says as much when it writes the weaker one.
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 · 84 lines · 56 tokens per session scan A cf8f3d179747
converge is a skill published in the GitHub repository raisedadead/claude-code-plugins (2 stars, last pushed 7d ago), licensed ISC. It adds 56 tokens to every session and 1,336 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…