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/jl-cmd/claude-dev-env/autoconvergenpx skills add jl-cmd/claude-dev-env --skill autoconvergegit clone --depth 1 https://github.com/jl-cmd/claude-dev-envWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jl-cmd/claude-dev-env/autoconverge)<a href="https://agentmods.dev/skills/jl-cmd/claude-dev-env/autoconverge"><img src="https://agentmods.dev/badge/skills/jl-cmd/claude-dev-env/autoconverge.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00125 | $0.05935 |
| Opus 5 | $0.00063 | $0.02967 |
| Sonnet 5 | $0.00025 | $0.01187 |
| Haiku 4.5 | $0.00013 | $0.00594 |
Grade A, and why
autoconverge 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 5d 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 — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autoconverge
One launch drives the whole loop to convergence. The /autoconverge skill
scans the tool list, selects a pacer (Workflow or portable), then resolves
PR scope, enters a worktree, grants project permissions, and drives the shared
converge product to ready (or a named blocker).
| Pacer | Host surface | How the loop runs |
|---|---|---|
workflow |
Tool list includes Workflow |
converge.mjs background pass; state in the workflow journal |
portable |
Workflow absent |
Continuous in-session ticks per ../_shared/pr-loop/portable-driver.md; same helpers and check_convergence.py ready definition |
pr-converge selects schedule_wakeup or portable the same way. Both
entry skills share the helper scripts and the convergence gate.
Run scope: one PR or several
Decide the scope from how many PRs the user named, then follow that path:
- One PR → the single-PR run described below: one worktree, one pacer
launch (
converge.mjsonpacer=workflow, portable continuous ticks onpacer=portable), one teardown. - Several PRs → the Multiple PRs run: on
pacer=workflow,workflow/converge_multi.mjsdrives every PR in parallel; onpacer=portable, run the portable driver once per PR (serial or host fan-out), then one teardown per PR.
The single-PR sections (Requirements, Pre-flight, Run the workflow or portable driver, Teardown) each describe one converge run. The multi-PR reference reuses them once per PR and adds only what fanning out needs: a per-PR worktree and a per-PR teardown loop.
Requirements
Scan the tool list for Workflow and ScheduleWakeup, then select the pacer:
python "$HOME/.claude/skills/_shared/pr-loop/scripts/select_converge_pacer.py" \
--skill autoconverge \
--has-workflow <0|1> \
--has-schedule-wakeup <0|1>
pacer=workflow— continue with Pre-flight and Run the workflow below.pacer=portable— continue with Pre-flight (portable worktree rules whenEnterWorktreeis absent), then the continuous driver in../_shared/pr-loop/portable-driver.md. Do not abort because the Workflow tool is missing.
What ships with it
50 files 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.
- .claude/CLAUDE.md 14 B
- AGENTS.md 1 B
- reference/.claude/CLAUDE.md 14 B
- reference/AGENTS.md 1 B
- reference/closing-report.md 8.2 KB
- reference/convergence-gates.md 848 B
- reference/convergence.md 12 KB
- reference/copilot-findings.md 3.0 KB
- reference/gotchas.md 3.9 KB
- reference/headless-safety.md 2.4 KB
- reference/multi-pr.md 6.2 KB
- reference/self-closing-loop.md 4.3 KB
- reference/stop-conditions.md 8.8 KB
- test_portable_pacer_gate.py 2.1 KB runs code
- workflow/.claude/CLAUDE.md 14 B
- workflow/AGENTS.md 1 B
- workflow/aggregate_runs.py 12 KB runs code
- workflow/autoconverge_report_constants/__init__.py 0 B runs code
- workflow/autoconverge_report_constants/.claude/CLAUDE.md 14 B
- workflow/autoconverge_report_constants/AGENTS.md 1 B
- workflow/autoconverge_report_constants/render_report_constants.py 18 KB runs code
- workflow/converge_multi.mjs 7.3 KB runs code
- workflow/converge_multi.run-input.test.mjs 5.8 KB runs code
- workflow/converge.clean-audit.test.mjs 32 KB runs code
- workflow/converge.codex-gate.test.mjs 21 KB runs code
- workflow/converge.contract.test.mjs 2.8 KB runs code
- workflow/converge.copilot-gate.test.mjs 47 KB runs code
- workflow/converge.fix-progress.test.mjs 4.5 KB runs code
- workflow/converge.fix-recovery.test.mjs 1.7 KB runs code
- workflow/converge.merge-conflict.test.mjs 797 B runs code
- workflow/converge.mjs 201 KB runs code
- workflow/converge.p2-advance.test.mjs 9.7 KB runs code
- workflow/converge.path-aware.test.mjs 2.1 KB runs code
- workflow/converge.precatch.test.mjs 11 KB runs code
- workflow/converge.run-input.test.mjs 3.7 KB runs code
- workflow/convergence_summary.py 3.8 KB runs code
- workflow/fixtures/wf_run/subagents/workflows/wf_881252e6-700/agent-a11d903476b803493.jsonl 1.4 KB
- workflow/fixtures/wf_run/subagents/workflows/wf_881252e6-700/agent-a26213978adeef6fb.jsonl 865 B
- workflow/fixtures/wf_run/subagents/workflows/wf_881252e6-700/agent-a3def0d15ed9d9110.jsonl 4.1 KB
- workflow/fixtures/wf_run/subagents/workflows/wf_881252e6-700/agent-a41f41b1b708ee3b7.jsonl 414 B
- workflow/fixtures/wf_run/subagents/workflows/wf_881252e6-700/agent-a758b880abecc3ff7.jsonl 766 B
- workflow/fixtures/wf_run/subagents/workflows/wf_881252e6-700/agent-a8897b89656b1bd16.jsonl 872 B
- workflow/fixtures/wf_run/subagents/workflows/wf_881252e6-700/agent-ab1c2d3e4f5a6b7c8.jsonl 2.0 KB
- workflow/fixtures/wf_run/subagents/workflows/wf_881252e6-700/agent-abd463d744a1437bc.jsonl 412 B
- workflow/fixtures/wf_run/subagents/workflows/wf_881252e6-700/agent-ad19d027ae8ee1816.jsonl 1.4 KB
- workflow/fixtures/wf_run/workflows/wf_881252e6-700.json 6.4 KB
- workflow/render_report.py 34 KB runs code
- workflow/test_aggregate_runs.py 4.6 KB runs code
- workflow/test_convergence_summary.py 4.6 KB runs code
- workflow/test_render_report.py 30 KB runs code
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.
- 5d ago First seen · 428 lines · 125 tokens per session scan A d067d008cdf5
autoconverge is a skill published in the GitHub repository jl-cmd/claude-dev-env (5 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 5,935 once invoked, about $0.0006 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…