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/ribeirogab/specwright/initnpx skills add ribeirogab/specwright --skill initgit 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 | $0.00094 | $0.01261 |
| Opus 5 | $0.00047 | $0.00630 |
| Sonnet 5 | $0.00019 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
init 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
init — set up specwright in this repository
The plugin already provides every workflow skill. This command creates only project-scoped content, and only what is missing:
- the
.specwright/vault; - a
## specwrightsection in the canonical AGENTS instructions, plus the Claude adapter symlink; - the ignore rules for the chosen mode.
That is the whole list. Role profiles are not project state — see step 5.
It never installs or enables a plugin, edits personal host configuration, copies
skill bodies, or creates .claude/settings.json.
Announce at start: "Setting up specwright..."
1. Resolve the plugin root
Resolve SW_PLUGIN_ROOT before any project write:
- use
PLUGIN_ROOTwhen it contains.codex-plugin/plugin.json; - otherwise use
CLAUDE_PLUGIN_ROOTwhen it contains.claude-plugin/plugin.json; - otherwise derive it from this loaded
skills/init/SKILL.mdreal path — the plugin root is two parents above theskills/init/directory.
Require scripts/sw_init.py and both templates/codex-agents/sw-*.toml beneath
that root. Stop before writing if resolution fails, and report the missing path.
Never look for bundled resources inside the target repository.
2. Pick the mode
Ask once, unless $ARGUMENTS already says shared or local:
- shared — specwright state is versioned with the project. Tracks
.specwright/,AGENTS.md,CLAUDE.md -> AGENTS.md, and the two Codex profiles. Ignores only.specwright/worktrees/. Pick this for your own repo. - local — specwright state stays private to this checkout. Uses
AGENTS.override.md,CLAUDE.local.md -> AGENTS.override.md, and ignores the whole vault, both instruction paths, and the profiles. Pick this for a repo you cannot or would rather not commit workflow artifacts to.
The canonical instruction file is always the AGENTS* path; the CLAUDE* path is
only a compatibility symlink, never the source of truth.
3. Run the scaffolder
python3 "$SW_PLUGIN_ROOT/scripts/sw_init.py" \
--project "$PWD" \
--mode "<shared-or-local>"
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 · 121 lines · 94 tokens per session scan A df9cd0f7df70
init is a skill published in the GitHub repository ribeirogab/specwright (3 stars, last pushed 24d ago), licensed MIT. It adds 94 tokens to every session and 1,261 once invoked, about $0.0005 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
review-depth
Decide how much review a change has earned, before reviewing it. Selects quick, standard, or deep from stated signals (reviewable changed lines, directory spread, trust-boundary risk flags, blast radius, documentation-only scope), reports the signal table and the rule that fired, then runs house-review at the selected…
doc-sync
Use when code has moved and the documentation may not have, or when a documentation set needs auditing for stale claims. Detects documentation drift by checking prose claims against repository facts, classifies every document as current-state (correctable), contract (report-only, human-owned) or ledger (skipped), and…
init-worktracking
Scaffold a portable, agent-optimized spec-driven work-tracking system into the current repository: AGENTS.md (global rules + agent reading protocol), a .tasks/ directory of atomic task files, and (by tier) ROADMAP.md, CHANGELOG.md, a validate.py checker, and thin CLAUDE.md/Cursor/Copilot pointers. Choose a footprint…
reconcile-worktrees
Safely consolidate one or more isolated git worktrees (for example left behind by parallel background agents, or from the fix-batch skill) into the main working tree, without committing or merging blindly. Use whenever asked to "reconcile the worktrees", "merge these agent branches", "bring the worktree changes back…
verifier-agent
Use before reconciling or landing an implementation to independently verify it against its approved spec and its task's acceptance criteria. Runs the declared verification commands and records each exact outcome, composes the spec-conformance lens so a contract divergence fails the run even when every command passes…
spec-author
Use when turning a raw idea, feature request, or bug into a persistent behavioral spec before any tasks or code. Drafts a scenario-based spec (problem, goals, non-goals, constraints, Given/When/Then scenarios with stable S-NNN ids, proposed surface, open questions), composes the spec-quality lens to self-check and…