Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ribeirogab/specwright/plugin install swWrote 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/ribeirogab/specwright/plan)<a href="https://agentmods.dev/skills/ribeirogab/specwright/plan"><img src="https://agentmods.dev/badge/skills/ribeirogab/specwright/plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ribeirogab/specwright/plan"><img src="https://agentmods.dev/badge/skills/ribeirogab/specwright/plan.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00076 | $0.01912 |
| Opus 5.5 | $0.00030 | $0.00765 |
| Sonnet 5.5 | $0.00015 | $0.00382 |
| Haiku 4.5 | $0.00008 | $0.00191 |
Grade A, and why
plan 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 1mo 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan — the technical plan, written for a stranger
Turn an approved proposal.md into the plan an implementer executes: tasks.md
always, and design.md when the change is large enough to have an architecture.
One rule governs every choice in this skill —
The implementer has no memory of the conversation that produced this plan.
That is not a hypothetical. The plan may be handed to a fresh session, a different model, a different host, or picked up next week. Anything that lives only in this conversation is lost the moment this skill ends. If it matters, it goes in the file.
Announce at start: "Writing the technical plan."
Resolve bundled resources
Resolve SW_PLUGIN_ROOT before reading a template or invoking the validator:
- use
PLUGIN_ROOTwhen it contains.codex-plugin/plugin.json; - otherwise use
CLAUDE_PLUGIN_ROOTwhen it contains.claude-plugin/plugin.json; - otherwise derive the root from this loaded
skills/plan/SKILL.mdreal path (two parents above theskills/plan/directory).
Require templates/design.md, templates/tasks.md, and
scripts/validate-change.sh beneath that root. Stop before writing if resolution
fails. Never look for bundled resources inside the target repository.
Locate the change
$ARGUMENTS names a change folder or slug → use it. Otherwise find the change in
.specwright/changes/*/ whose proposal.md says status: pending or
in-progress; several → ask which. Set status: in-progress when you start.
Every change lives flat at .specwright/changes/YYYY-MM-DD-<slug>/, standalone
or delivery-linked alike.
Read what came before
For a change that belongs to a delivery, read the ## Decisions and discoveries
section of every sibling change already shipped — the changes whose
delivery: points at the same delivery folder. Those are facts an earlier change
paid to discover: data formats, surprising behaviors, required workarounds,
constraints that only appear at runtime. Fold every applicable one into this
plan's Architecture or Constraints. A plan that trips over a recorded discovery
is a review blocker.
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.
- 1mo ago First seen · 187 lines · 76 tokens per session scan A b14134d699b5
plan is a skill published in the GitHub repository ribeirogab/specwright (3 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,912 once invoked, about $0.0003 per session on Opus 5.5. 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
template-sia
SIA (Self-Improvement Agent) harness exemplar — Meta/Target/Feedback loops, public/private splits, fixture replay, fail-closed validation.
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…
systematic-debugging
Use when a defect, test failure, flaky test, or unexpected behavior needs its cause established before anyone writes a task file or a fix. Reproduces the report first, localizes the failure to the boundary where behavior diverges, then tests one hypothesis at a time and returns a deterministic verdict, so a run that…
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…