plan-consolidation

plan-consolidation is a skill for Claude Code from wsauret/flywheel. It costs 53 tokens per session (3,046 once invoked), scanned A, original, MIT.

A procedure for updating an active implementation plan with a reviewer's findings while keeping a backup of the original plan. The plan is stored as structured JSON in a session directory.

In plain words
What is it for?
Use it to consolidate or finalize a plan after review, merge the findings into spec.json, and preserve the earlier specification for auditing.
Why use it?
It incorporates review feedback without losing the pre-review version, and it reports when the required planning files are missing.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the flywheel plugin — 15 skills, 15 agents shipped together

Good fit Use it to consolidate or finalize a plan after review, merge the findings into spec.json, and preserve the earlier specification for auditing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wsauret/flywheel/plan-consolidation
Install

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.

Any agent
npx skills add wsauret/flywheel --skill plan-consolidation
Clone the repo
git clone --depth 1 https://github.com/wsauret/flywheel

Made for: Claude Code.

Or install flywheel, the plugin that ships this one along with the rest of its 15 skills, 15 agents.

Wrote 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.

agentmods badge for plan-consolidation

README.md
[![agentmods](https://agentmods.dev/badge/skills/wsauret/flywheel/plan-consolidation.svg)](https://agentmods.dev/skills/wsauret/flywheel/plan-consolidation)
Your own site
<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>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,046 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 76c2f274b8c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

flywheel/skills/plan-consolidation/SKILL.md · 218 lines

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

  1. Read .flywheel/plugin/active.json to resolve session_id
  2. Compute session directory: .flywheel/plugin/sessions/<session_id>/
  3. Read two inputs:
    • spec.json (the pre-refinement spec)
    • review.findings.json (written by plan-review)

Errors:

  • active.json missing → ask the user to run plan-creation first
  • review.findings.json missing → ask the user to run plan-review first, or abort
  • spec.json missing → 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:

  1. review.findings.json.open_questions (entries the synthesizer could not resolve)
  2. 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.

Read the full file on GitHub · 218 lines

Changes

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.

  1. 8d ago First seen · 218 lines · 53 tokens per session scan A 76c2f274b8c3

Subscribe to this mod's changes

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.

Related

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.

Hmbown/Codewhale · 44 tokens

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.

Hmbown/Codewhale · 47 tokens

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.

Hmbown/Codewhale · 52 tokens

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.

Hmbown/Codewhale · 48 tokens

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.

Hmbown/CodeWhale · 32 tokens

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.

Hmbown/CodeWhale · 57 tokens