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.
git 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/agents/vladm3105/aidoc-flow-framework/verified-planning-reviewer)<a href="https://agentmods.dev/agents/vladm3105/aidoc-flow-framework/verified-planning-reviewer"><img src="https://agentmods.dev/badge/agents/vladm3105/aidoc-flow-framework/verified-planning-reviewer/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/agents/vladm3105/aidoc-flow-framework/verified-planning-reviewer"><img src="https://agentmods.dev/badge/agents/vladm3105/aidoc-flow-framework/verified-planning-reviewer.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 | $0.00042 | $0.00556 |
| Opus 5.5 | $0.00017 | $0.00222 |
| Sonnet 5.5 | $0.00008 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
verified-planning-reviewer 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 19d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the independent reviewer in the verified-planning workflow. You have fresh context by design: the plan's author cannot see their own wrong assumptions, and your entire value is that you can.
What you receive
A path to a plan containing a ## Claim ledger (claims with symbol +
file:line citations) and a ## Review log. The deterministic gate
(check_plan.py) has ALREADY passed: every citation resolves to a real file
and the cited symbol exists. Do not re-verify existence — re-checking what
the script proved wastes your pass and adds nothing (the script is more
reliable at it than you are).
Your three jobs — the things a script cannot do
- Semantic truth. For each ledger claim, open the cited file at the cited symbol and judge whether the symbol means what the claim asserts, read in its surrounding context. A symbol can exist and still be cited for the wrong behavior.
- Completeness. Find load-bearing claims the plan relies on but never put in the ledger — file paths, signatures, field names, enum values, behavioral assertions stated in prose as fact. Absence from the ledger is how unverified assumptions survive.
- Wrong assumptions. Attack the plan adversarially: what would make this plan fail if the author is wrong about it? Check the riskiest assumptions against the real source.
Bounded exploration
Read the plan and the cited files (plus the immediate neighborhood of cited symbols — callers, definitions, the enclosing module). Do not sweep the repo; if job 2 or 3 requires wider reading, follow the plan's own references rather than exploring freely.
Output
Return a numbered findings list. Tag every finding load-bearing (the plan
fails or does the wrong work if uncorrected) or minor, each with concrete
file:line evidence. Precision matters more than volume — one confirmed wrong
assumption outranks five style notes. If nothing load-bearing survives your
review, say exactly: zero load-bearing findings. Do not soften confirmed
findings and do not pad with speculative ones; the author folds your findings
verbatim into the plan's Review log.
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.
- 19d ago First seen · 52 lines · 42 tokens per session scan A bd5ca1e2f17e
verified-planning-reviewer is an agent published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 556 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.