plan-attest

A command that records a SHA-256 hash, a fixed digital fingerprint, of the active task plan. Later hooks compare the plan with that fingerprint before providing its contents to the agent.

In plain words
What is it for?
It helps attest, inspect, or clear the verification record for a task plan in parallel-plan or legacy planning setups.
Why use it?
It can detect changes to the plan and block its automatic injection when the file no longer matches the recorded version.

Command

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 commands/othmanadi/planning-with-files/plan-attest
Clone the repo
git clone --depth 1 https://github.com/OthmanAdi/planning-with-files
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 402 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 $0.00064 $0.00402
Opus 5 $0.00032 $0.00201
Sonnet 5 $0.00013 $0.00080
Haiku 4.5 $0.00006 $0.00040

Measured yesterday against content hash ae3f009bdfd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-attest 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 yesterday.

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.

commands/plan-attest.md · 25 lines

What it actually says

Run the plan attestation helper for the active plan.

Steps:

  1. Resolve the active plan: prefer ${PLAN_ID} env var, then .planning/.active_plan, then newest .planning/<dir>/, then legacy ./task_plan.md.
  2. Compute the SHA-256 of the resolved task_plan.md.
  3. Write the hex digest to .planning/<active-plan>/.attestation (parallel-plan mode) or ./.plan-attestation (legacy mode).
  4. Confirm to the user with the short hash (first 12 hex chars) and the storage path.

Implementation:

  • On Linux/macOS/Git Bash: sh ${CLAUDE_PLUGIN_ROOT}/scripts/attest-plan.sh
  • On Windows PowerShell plugin installs: & "$env:CLAUDE_PLUGIN_ROOT\scripts\attest-plan.ps1"
  • On Windows PowerShell standalone installs: & "$env:USERPROFILE\.claude\skills\planning-with-files\scripts\attest-plan.ps1"

Flags:

  • --show — print the currently stored hash and where it lives.
  • --clear — remove the attestation (re-open the plan to free editing).

After running this command, every UserPromptSubmit and PreToolUse hook fire compares task_plan.md against the stored hash. If they diverge, the hook emits [PLAN TAMPERED — injection blocked] instead of feeding plan content into the model. Re-run /plan-attest whenever you intentionally edit and re-approve the plan.

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. yesterday First seen · 25 lines · 64 tokens per session scan A ae3f009bdfd3

Subscribe to this mod's changes

plan-attest is a command published in the GitHub repository OthmanAdi/planning-with-files (26,438 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 402 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.