Borrowing it
Nothing to install: this file belongs to vladm3105/aidoc-flow-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vladm3105/aidoc-flow-framework/dev/.agents/skills/verified-planning/SKILL.mdgit clone --depth 1 https://github.com/vladm3105/aidoc-flow-frameworkWrote 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/vladm3105/aidoc-flow-framework/verified-planning)<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/verified-planning"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/verified-planning/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/vladm3105/aidoc-flow-framework/verified-planning"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/verified-planning.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 | $0.00038 | $0.02928 |
| Opus 5.5 | $0.00015 | $0.01171 |
| Sonnet 5.5 | $0.00008 | $0.00586 |
| Haiku 4.5 | $0.00004 | $0.00293 |
Grade A, and why
verified-planning 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 10d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verified Planning
Muse project-skill port of the canon global skill. Source:
aidoc-flow-claude-agents-config/skills/verified-planning/SKILL.md. Wording mirrorsframework/skills/verified-planning/SKILL.md(engine-agnostic adaptation). The gate runs from this directory:python3 .agents/skills/verified-planning/check_plan.py <plan>. Where the canon names a Claude-specific agent type, use Muse's fresh-context read-only subagent equivalent and keep the independence contract.
Plan-review rules get ritualized: the author writes "Pass 1/Pass 2" from memory and finds nothing, because the author cannot see their own wrong assumption. This skill replaces ritual with two forcing functions.
0. Where the plan lives
A development plan lives in the owning repo's plans/ directory, named per
that repo's convention (PLAN-NNN_slug.md) — never in docs/superpowers/ and
never in an aggregator/umbrella repo that holds no development of its own (the
aidoc-flow umbrella is one instance, not the rule). This convention
takes priority over any generic plan skill's default location.
1. Draft with a Claim ledger
Every load-bearing claim in the plan — a file path, a function/method
signature, a field or key name, an event/enum value, or a behavioral assertion
("validator X ignores unknown keys", "the loop reads only Y") — goes in a
## Claim ledger table with the file:line you actually opened and read:
| # | Claim | Symbol | Citation |
|---|---|---|---|
| 1 | completion is recorded as a log event | task_completed |
src/orchestrator/loop.py:223 |
A claim you have not verified is written UNVERIFIED in the Citation column and
cannot survive to ready. Do not guess a line number — open the file.
A claim that source CANNOT settle is written PROBE: <command>. Some claims
are live facts — a server-side setting, an API behaviour, a runtime observation.
Reading the repository harder will never answer them, and before this state
existed the only options were to guess in prose or to stall the plan forever.
Authors guessed: one plan answered the same unmeasurable question three
different ways across three review passes, each fold retracting the last.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago Changed · +9 lines 422ee77ff70b
- 1mo ago First seen · 192 lines · 38 tokens per session scan A 4ad52424792f
verified-planning is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 2,928 once invoked, about $0.0002 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 2026-09-28.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…