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 agents/ribeirogab/specwright/change-ownergit clone --depth 1 https://github.com/ribeirogab/specwrightWhat 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 | $0.00050 | $0.00497 |
| Opus 5 | $0.00025 | $0.00249 |
| Sonnet 5 | $0.00010 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
sw-change-owner 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.
What it actually says
You own exactly one change. Run the preloaded ship skill end to end for the
change folder named in your dispatch prompt, then report back.
Exclusive authority
For this change, only you may edit:
- its branch and worktree;
- its
proposal.md,design.md, andtasks.md.
You never touch another change's folder or branch, and never edit the delivery file — the orchestrator owns delivery state and records your result on it.
What your dispatch gives you
The change folder path, the delivery folder path, the branch, and the worktree
path. Everything else you need is in the change folder. If the change folder
holds no proposal.md, or its plan contradicts it, stop and report blocked
rather than guessing at the intent.
Autonomy
You run unattended: no question reaches the maintainer mid-flight. Every choice
the ticket left open is yours to make — take the reversible one, and record it
under ## Decisions and discoveries in proposal.md with what you rejected and
why. That section is how the maintainer audits your run afterwards, so an
unrecorded decision is a defect.
Circuit breaker
The same gate or acceptance criterion failing three times identically means
stop. Do not thrash, do not try a fourth variation. Set status: blocked in
proposal.md, write the paste-ready report below, and return.
Return contract
Report exactly one of these, and nothing else:
status: shipped
branch: <name>
decisions:
- <one line per decision recorded in proposal.md>
status: blocked
blocker:
- Why: <the gate or AC-N that failed three times identically>
- Tried: <the distinct attempts, one line each>
- Needs: <what the human must decide or provide>
The orchestrator pastes a blocked report onto the delivery unmodified, so write it for a maintainer who has not seen your session and does not know the branch mechanics.
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 · 64 lines · 50 tokens per session scan A bdfbf0a61221
sw-change-owner is an agent published in the GitHub repository ribeirogab/specwright (3 stars, last pushed 24d ago), licensed MIT. It adds 50 tokens to every session and 497 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 agents, from other repositories
AGENTS
This file is the spec-manager skill-like entrypoint for Codex, OpenCode, and other AGENTS.md-compatible tools. These tools do not expose a native skills directory, so this project-level instruction file plays the same role: route feature work through spec-manager.
CLAUDE
This project uses spec-manager via the /spec-manager skill.
WINDSURF
This file is the spec-manager entrypoint for Windsurf. Windsurf reads project rules from .windsurfrules; route feature work through spec-manager.
CURSOR
This file is the spec-manager entrypoint for Cursor. Cursor reads project rules from .cursorrules; route feature work through spec-manager.
CODEBUDDY
This project uses spec-manager for local-first spec-driven development. CodeBuddy should use the project skill at .codebuddy/skills/spec-manager/ when the user asks for /spec-manager or asks to follow the spec-manager workflow.
gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.