update-plan

A command for updating a project's written plan and progress log from the current repository state and conversation. It works with files such as PLAN.md and PROGRESS.md.

In plain words
What is it for?
Use it to check repository status, update completed and pending plan items, record new project work, and append a dated progress entry.
Why use it?
It keeps project notes aligned with completed work, newly identified tasks, and the current Git state instead of relying on memory.

Command for Claude Code

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/vstorm-co/memv/update-plan
Clone the repo
git clone --depth 1 https://github.com/vstorm-co/memv

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 444 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 $0.00011 $0.00444
Opus 5 $0.00005 $0.00222
Sonnet 5 $0.00002 $0.00089
Haiku 4.5 $0.00001 $0.00044

Measured 3d ago against content hash c472fdd9c132, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-plan 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 3d 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.

.claude/commands/update-plan.md · 43 lines

What it actually says

Update notes/PLAN.md and append to notes/PROGRESS.md based on the current state of the repository and this conversation.

Process

  1. Run ~/.claude/scripts/plan-status.sh to get structured plan status and git state
  2. Read notes/PLAN.md (previous version — update it, never rewrite from scratch)
  3. Review the conversation for decisions, priorities, and tasks discussed
  4. Optionally scan recent session logs in notes/claude/worklog/ for additional context
  5. Update notes/PLAN.md:
    • Flip [ ][x] for items completed (verified in codebase, not just discussed)
    • Add new [ ] items if new work was identified
    • Remove items that are no longer relevant
    • Update the "Last updated" timestamp
  6. Append to notes/PROGRESS.md (create if missing):
    • Add a dated entry summarizing what changed in the plan and why
    • This file is append-only — never rewrite or remove previous entries

Rules

  • Project-scoped only — only include work that changes this project's code, tests, docs, or architecture. Exclude personal tooling, editor config, etc.
  • Preserve structure — don't reorganize sections or rewrite prose unless explicitly asked. Only touch checkboxes and add/remove items.
  • Verify before checking off — mark items [x] only if the work is actually in the codebase (committed or staged), not just discussed.
  • Ground updates in actual repo state (commits, diffs), not just conversation

PROGRESS.md format

## YYYY-MM-DD

- Checked off: <item> — <brief evidence>
- Added: <new item> — <why>
- Removed: <item> — <why>
- Decision: <what was decided and why>

Keep entries concise. One line per change.

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. 3d ago First seen · 43 lines · 11 tokens per session scan A c472fdd9c132

Subscribe to this mod's changes

update-plan is a command published in the GitHub repository vstorm-co/memv (89 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 444 once invoked, about $0.0001 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.