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/inkatze/planwright/self-reviewnpx skills add inkatze/planwright --skill self-reviewgit clone --depth 1 https://github.com/inkatze/planwrightWrote 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/inkatze/planwright/self-review)<a href="https://agentmods.dev/skills/inkatze/planwright/self-review"><img src="https://agentmods.dev/badge/skills/inkatze/planwright/self-review.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 | $0.00084 | $0.03740 |
| Opus 5 | $0.00042 | $0.01870 |
| Sonnet 5 | $0.00017 | $0.00748 |
| Haiku 4.5 | $0.00008 | $0.00374 |
Grade A, and why
self-review 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 4d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/self-review
One complete review pass of the feature branch against its base, wired into
planwright's act-then-review autonomy gate (REQ-E2.1, D-12): Discovery Rigor
produces the finding list, Validation Rigor confirms it, the finding
categorization routes each confirmed finding to a disposition, and the gate
wiring's audit record is the handoff. /polish iterates it to convergence;
this skill is the single pass.
Doctrine
This skill is procedure, not doctrine. Resolve these rule docs via
the rule-doc resolution convention
(scripts/resolve-rule-doc.sh <doc-name> under the resolved planwright root,
or the documented PLANWRIGHT_ROOT/CLAUDE_PLUGIN_ROOT chain); their
definitions govern wherever this skill names a concept:
discovery-rigor— lens checklist, lens-coverage table, tool-grounded discovery, fan-out, self-critique passvalidation-rigor— the three identification passes plus the adversarial bi-directional re-validation; solution validation, including the altitude check, with surface-relative whole-system end-to-end reproduction preferredfinding-categorization— the four buckets, their predicates, hard pauses and the hard-disqualifier zones, declined-with-rationale, the resolution laddergate-wiring— routing order, commit discipline, checklist and audit formats, ladder procedure, pause protocol, loop-end handoff, PR-body assemblyresearch-rigor(point-of-use),refactor-instinct(review mode),security-posture(artifact data-hygiene),proportionality(declared scoping)
If a rule doc does not resolve, halt with a clear message naming the missing doc and the resolution chain consulted.
Doctrine manifest (the reading model above in machine-parseable form, per
doctrine/instruction-hygiene.md; run-start docs load before work begins,
point-of-use at the named step):
Doctrine: run-start discovery-rigor Doctrine: run-start validation-rigor Doctrine: run-start finding-categorization Doctrine: run-start gate-wiring Doctrine: point-of-use research-rigor (the Validation step, where research triggers fire) Doctrine: run-start refactor-instinct Doctrine: run-start security-posture Doctrine: run-start proportionality
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.
- 4d ago First seen · 295 lines · 84 tokens per session scan A 3aa6079472f4
self-review is a skill published in the GitHub repository inkatze/planwright (3 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 3,740 once invoked, about $0.0004 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
defect-hunting
Use when reviewing code, auditing an app, writing a guard rule or test, or certifying any threshold/constant/formula. Finds the defects a diff review structurally cannot see — the second write path, the mis-calibrated constant, the rule that cannot fail. Triggers from code-reviewer, /app-audit, qa-engineer…
role-activation
Use at project start — /app-init, /app-onboard, or /app-run's first step — to decide which of the roles this product actually needs, and to write the durable roster the rest of the flow reads. Triggers whenever a command is about to fan out to a team, or a gate is about to run for a role that may not be on this…
team-protocol
Use whenever one role needs something from another role — a blocker, a spec question, a cross-platform divergence, a handoff, or an escalation. Defines the durable team message ledger, who may talk to whom, the anti-ping-pong guard, and when to escalate to the user instead. Triggers from every agent that would…
parallel-orchestrator
Use to actually launch multiple developer agents in parallel via the subagent tool (Task/Agent), given a sprint plan and board. Triggers from /app-build or when the tech-manager says "spawn the pod". Encapsulates the rules for safe concurrent agent execution.
agent-isolation
Use before spawning any agent that writes files, and by every developer/fixer agent as its first and last action. Gives each agent its own git worktree, forbids blanket staging, and requires confirming a mutation actually landed. Triggers from /app-build, /app-audit, parallel-orchestrator, and any parallel agent…
sprint-planner
Use to convert the backlog into a runnable sprint with parallel ticket assignment and dependency tracking. Used primarily by the tech-manager. Triggers on "plan the sprint", "what does the pod do next", or as part of /app-build.