plan-update

A command that adds a decision or risk to a project's structured plan. It translates a free-form request into the JSON format expected by the project's plan tool.

In plain words
What is it for?
Use it to record architectural decisions, risks, their reasoning, and optional dates in sitrep/PROJECT_PLAN.md.
Why use it?
It removes manual editing of plan tables and keeps project decisions and risks recorded consistently. It can also create an initial plan when the project does not have one.

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/viitorohit/sitrep/plan-update
Clone the repo
git clone --depth 1 https://github.com/viitorohit/sitrep

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 451 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 $0.00000 $0.00451
Opus 5 $0.00000 $0.00226
Sonnet 5 $0.00000 $0.00090
Haiku 4.5 $0.00000 $0.00045

Measured 2d ago against content hash 3f05db554330, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-update 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.

.claude/commands/plan-update.md · 35 lines

What it actually says

Update Project Plan

Intentional (manually invoked).

Thin wrapper (GETSITREP-10) over getsitrep plan-update — the CLI owns the table lookup, row insertion, and commit. This file's only remaining job is the one step no CLI can do on its own: interpreting the free-form request in $ARGUMENTS into the structured JSON the CLI expects.

No PROJECT_PLAN.md yet? (GETSITREP-25 plan-presence guard)

If sitrep/PROJECT_PLAN.md doesn't exist, running getsitrep plan-update with no --data triggers a guard: interactively it asks to generate a draft from repo introspection, but an AI-driven invocation won't have a real TTY to answer that prompt — use the non-interactive form directly instead:

getsitrep plan-update --generate --brief "<one-line description, optional>"

This generates a draft from package.json/README.md/git config and writes it — safe to call, it never overwrites an existing plan. Skip Steps 1-2 below in this case.

Step 1: Interpret the request

Read $ARGUMENTS. Determine whether it describes a decision or a risk:

  • Decision{"type": "decision", "decision": "...", "rationale": "...", "date": "YYYY-MM-DD"?} (date optional, defaults to today)
  • Risk{"type": "risk", "risk": "...", "impact": "High"|"Medium"|"Low", "mitigation": "..."}

If it's genuinely ambiguous which one applies, or a required field is missing from the request, ask the user rather than guessing.

Note: adding a task to a phase or the Future table is /capture's job, not this command's — if the request is really "add a task," say so and suggest /capture instead of forcing it into this shape.

Step 2: Call the CLI

getsitrep plan-update --data '<the JSON from Step 1>'

Print its output verbatim.

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 · 35 lines · 0 tokens per session scan A 3f05db554330

Subscribe to this mod's changes

plan-update is a command published in the GitHub repository viitorohit/sitrep (19 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 451 tokens. 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.