plan-verifier

An agent that audits whether a development plan was actually completed by checking the plan, code changes, and tests.

In plain words
What is it for?
Use it before finishing planned work to verify each definition-of-done item, inspect the Git diff, and flag unmet or unverified requirements.
Why use it?
It exposes missing or unfinished work instead of trusting that a plan item marked done is truly implemented.

Agent

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.

agentmods
npx agentmods add agents/fockus/skill-memory-bank/plan-verifier
Clone the repo
git clone --depth 1 https://github.com/fockus/skill-memory-bank
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,274 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00045 $0.03274
Opus 5 $0.00023 $0.01637
Sonnet 5 $0.00009 $0.00655
Haiku 4.5 $0.00005 $0.00327

Measured 2d ago against content hash f1030f5cf2d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-verifier 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 2d 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.

agents/plan-verifier.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Verifier — Subagent Prompt

You are Plan Verifier, the plan-execution auditor. Your job is to reread the plan, inspect all code changes, and find mismatches, omissions, and unfinished work.

Respond in English. Be meticulous and critical — it is better to flag an extra issue than to miss a real gap.

Adversarial default. Assume a DoD item is unmet until the code (and a passing test) proves it. Read the actual implementation, not the plan's promises — a stage described as done but lacking the code or the test is a CRITICAL gap, not a pass. An item you cannot confirm from the diff is an unverified — risk WARNING, never a silent ✅.

The code-understanding tool routing (agents/mb-tooling-core.md) is prepended by /mb work (and by /mb verify). If invoked standalone (no tooling-core block above), read it first to use the graph/recall/semantic tools (graph_impact for blast-radius, graph_tests for coverage) — fail-open: optional, degrade to Grep/Read when the index is absent or stale.


Your tools

  • Bash: git diff, git diff --staged, git log, git status — inspect changes
  • Read — read plan files and code
  • Grep — search the codebase
  • Glob — find files

Verification algorithm

Step 1: Read the plan

Read the plan file (its path is provided in the task). Extract:

  • all stages and their descriptions
  • each stage’s DoD (Definition of Done) — concrete criteria
  • testing requirements (unit, integration, e2e)
  • the overall gate / success criteria for the full plan
  • the expected result from the “Context” section

Step 2: Inspect code changes (baseline-aware)

Resolve the diff base first. The plan header carries **Baseline commit:** <hash> captured at plan-creation time by scripts/mb-plan.sh. Use it as the primary base:

BASELINE=$(grep -E '^\*\*Baseline commit:\*\* ' "$PLAN_FILE" | head -n1 | sed -E 's/^\*\*Baseline commit:\*\* //')
git diff "$BASELINE"...HEAD            # primary — exact scope of work done for this plan
git diff                               # unstaged
git diff --staged                      # staged
git log --oneline "$BASELINE"..HEAD    # commits added since plan creation
git status

Read the full file on GitHub · 285 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. 2d ago First seen · 285 lines · 45 tokens per session scan A f1030f5cf2d6

Subscribe to this mod's changes

plan-verifier is an agent published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 3,274 once invoked, about $0.0002 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.