Plan Attest

Lock the current task_plan.md content with a SHA-256 attestation. Hooks then refuse to inject plan content if the file diverges from the attested hash, blocking silent tampering. Use --show to print the stored hash, --clear to remove the attestation. Available since v2.37.0.

Published by @OthmanAdi·from OthmanAdi/planning-with-files·0 agent reads / 30d·0 saves·

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 ${CLAUDE_PLUGIN_ROOT}/scripts/attest-plan.sh
  • On Windows PowerShell: & "$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.

Bundled with this artifact

2 files

Reference files that ship alongside this artifact. Agents pull these in only when the task needs them.

More on the bench

SKILL▲0

Sendblue Notify

Text the user's phone when a long-running task, agent turn, or scheduled job finishes — via @sendblue/cli for outbound, optionally wired to a Claude Code Stop hook for automatic fire.

software-engineering+2
⊙ 1
SKILL▲0

Onboard

/cs:onboard — Founder interview that populates ~/.claude/company-context.md using the canonical 7-dimension cs-onboard schema. The first command to run when starting with c-level-agents. Use when setting up the virtual C-suite for a new company, or when advisors lack company context — e.g. before a first /cs:boardroom or after a fundraise changes the numbers.

ai-prompt-engineering+2
⊙ 1
SKILL▲0

Planning With Files

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+ tool calls. Supports automatic session recovery after /clear.

ai-prompt-engineering+1
⊙ 0