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 commands/agentic-swe/agentic-swe/installgit clone --depth 1 https://github.com/agentic-swe/agentic-sweWhat 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 | $0.00023 | $0.01461 |
| Opus 5 | $0.00012 | $0.00731 |
| Sonnet 5 | $0.00005 | $0.00292 |
| Haiku 4.5 | $0.00002 | $0.00146 |
Grade A, and why
install 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/install
Plugin-first setup for a target git repository using the agentic-swe Claude Code plugin.
The pipeline markdown (commands, phases, agents including bundled helpers under agents/plugin-runtime/, templates, references, hooks, state-machine.json, …) ships inside the installed plugin and is resolved via ${CLAUDE_PLUGIN_ROOT}/.... You do not copy that tree into project/.claude/ as the primary path.
Prompt
1. Enable the plugin
- Distribution: Add this repository as a Claude Code plugin marketplace and install
agentic-swe(see project docs for the marketplace name and/plugin installflow). - Local development: Run Claude Code with
claude --plugin-dir <path-to-this-repo-root>so the plugin root matches the repository layout (commands/,phases/,agents/, … at the repo root).
2. Project policy (CLAUDE.md)
- Automation (shells, Cursor install, CI): from a checkout of this pack, run
node scripts/merge-claude-policy.js --target /path/to/target-repo(optional--gitignoreto append.worklogs/to.gitignorewhen missing). The Cursor install script runs the same merger whenAGENTIC_SWE_TARGET_REPOis set — see the Cursor plugin doc on the project site. - If the target repo has no root
CLAUDE.md: offer to add one by copying or summarizing the Hypervisor policy from this pack’s rootCLAUDE.md(or tell the user to copy it manually). - If
CLAUDE.mdalready exists: append (do not replace) the pipeline policy using this delimiter convention:
---
<!-- BEGIN autonomous-swe-pipeline policy -- do not edit above this line -->
- If the delimiter
<!-- BEGIN autonomous-swe-pipeline policyis already present: replace only the content after the delimiter with the current policy text (upgrade path).
3. Work state: .worklogs/<id>/
Per-work artifacts (state.json, progress.md, audit.log, phase outputs) live under .worklogs/<id>/ at the target repository root (not under .claude/).
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 · 76 lines · 23 tokens per session scan A a028cf4b3359
install is a command published in the GitHub repository agentic-swe/agentic-swe (5 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 1,461 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.