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 skills add wsauret/flywheel --skill plan-consolidationgit clone --depth 1 https://github.com/wsauret/flywheelWrote 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/wsauret/flywheel/plan-consolidation)<a href="https://agentmods.dev/skills/wsauret/flywheel/plan-consolidation"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/plan-consolidation.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 188 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00053 | $0.03046 |
| Opus 5 | $0.00026 | $0.01523 |
| Sonnet 5 | $0.00011 | $0.00609 |
| Haiku 4.5 | $0.00005 | $0.00305 |
Grade A, and why
plan-consolidation 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 8d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Consolidation Skill
Merge review findings into the active session's spec.json. Pre-refinement spec is preserved as a .pre-consolidation sidecar so the refinement is auditable (D7). The refined spec.json retains the same top-level shape as the pre-refinement spec — only the content changes. Do NOT add top-level fields like origin, risks, or notes; the schema rejects additional properties. Namespace: plugin uses .flywheel/plugin/sessions/.
Input
No arguments. Reads the active session from .flywheel/plugin/active.json.
Phase 0: Load Active Session
- Read
.flywheel/plugin/active.jsonto resolvesession_id - Compute session directory:
.flywheel/plugin/sessions/<session_id>/ - Read two inputs:
spec.json(the pre-refinement spec)review.findings.json(written by plan-review)
Errors:
active.jsonmissing → ask the user to run plan-creation firstreview.findings.jsonmissing → ask the user to run plan-review first, or abortspec.jsonmissing → the session is broken; ask the user to delete and restart
Phase 1: Back Up to Sidecar (D7)
cp .flywheel/plugin/sessions/<id>/spec.json \
.flywheel/plugin/sessions/<id>/spec.json.pre-consolidation
Cleaned on ship.
Phase 2: No-Op Check
If review.findings.json has zero findings and zero open questions:
- Print: "No refinements needed — spec is already work-ready."
- Skip to Phase 6 (next-steps prompt).
Phase 3: Surface Open Questions
Questions to surface:
review.findings.json.open_questions(entries the synthesizer could not resolve)- Inter-reviewer conflicts — findings where two or more reviewers described the same issue but assigned different severities. Surface the divergence; the user decides which severity is right rather than defaulting to the more severe.
BLOCKING: Each AskUserQuestion call MUST contain exactly ONE question. Never pass multiple questions to a single AskUserQuestion call (no questions: [...] arrays of length > 1). Make a separate call per question, await the response, then make the next call. Bundled multi-question prompts produce a confusing wizard-style "Review your answers / Submit" review flow that breaks both UX and test automation.
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.
- 8d ago First seen · 218 lines · 53 tokens per session scan A 76c2f274b8c3
plan-consolidation is a skill published in the GitHub repository wsauret/flywheel (14 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 3,046 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 2026-08-30.
Other skills, from other repositories
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
cw-slice
Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.
cw-dogfood
Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
best-of-n
Generate a small set of independent candidate solutions in worktrees, judge them against one explicit rubric, and apply the winner only after PASS verification.
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.