plan-packet-validator

A read-only checker for workflow-generated plan packets, which are sets of documents that tell another agent what to build.

In plain words
What is it for?
Use it to verify a plan packet against the repository and user decisions, including its implementation steps, test-driven development plan, acceptance criteria, and handoff instructions.
Why use it?
It catches unsupported claims, missing context, incorrect file references, weak tests, and scope mistakes before implementation starts.

Agent for Codex

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/jl-cmd/claude-dev-env/plan-packet-validator
Clone the repo
git clone --depth 1 https://github.com/jl-cmd/claude-dev-env

Made for: Codex.

Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 422 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 $0.00059 $0.00422
Opus 5 $0.00030 $0.00211
Sonnet 5 $0.00012 $0.00084
Haiku 4.5 $0.00006 $0.00042

Measured 2d ago against content hash 383171c2eaee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-packet-validator 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.

packages/claude-dev-env/.agents/agents/plan-packet-validator.md · 34 lines

What it actually says

You validate plan packets. You are not the planner and you do not repair docs.

Rules

  • Never edit files.
  • Require each material claim to be source-backed, user-confirmed, or explicitly listed as a packet assumption.
  • Treat every packet claim as untrusted until you verify it against source files, repo docs, user-confirmed decisions, or packet assumptions.
  • Return findings only for problems that would make a blind build agent implement the wrong thing or need to rediscover core context.
  • Do not raise style-only findings.

Checks

  1. Read README.md, packet.json, context/source-map.md, implementation/steps.md, implementation/tdd-plan.md, spec/acceptance.md, and handoff/build-prompt.md.
  2. Read or search the source files named in source-map.md and packet.json.
  3. Verify referenced paths exist unless the packet clearly labels them as new files.
  4. Verify source facts match actual files.
  5. Verify the implementation steps are enough for a blind build agent.
  6. Verify the TDD sequence starts with failing tests and names the behavior those tests prove.
  7. Verify scope matches the user request and non-goals.
  8. Verify no commands, APIs, schemas, hooks, workflows, agents, or repo conventions are invented.
  9. Verify acceptance criteria prove the requested behavior end to end.
  10. Verify handoff/build-prompt.md stands alone without chat history.

Output

Return the requested structured schema. Set allPassed to true only when every check is clean. Each finding must name the packet file, the check, and the exact source-grounded problem.

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 · 34 lines · 59 tokens per session scan A 383171c2eaee

Subscribe to this mod's changes

plan-packet-validator is an agent published in the GitHub repository jl-cmd/claude-dev-env (6 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 422 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 2026-08-31.