Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/update-state.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/update-state)<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/update-state"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/update-state/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/update-state"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/update-state.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02176 |
| Opus 5.5 | $0.00000 | $0.00870 |
| Sonnet 5.5 | $0.00000 | $0.00435 |
| Haiku 4.5 | $0.00000 | $0.00218 |
Grade A, and why
update-state 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update State — Safely edit a repo's planning/state.json per the canonical schema.
Purpose
planning/state.json is the authoritative work-block dependency graph for a repo — not a status
report. Almost every planning command (/generate-master-plan, /plan, /chore, /ticket,
/start-block, /handoff, /wrap-up, /backlog-ticket, a manual fix after mev validate-brain --state flags something) ends up editing part of it. This command is the one place that spells out
how to do that safely, so every agent edits the same file the same way instead of re-deriving the
rules from scratch (or worse, guessing).
The schema itself lives in one place — do not duplicate its field shapes here or anywhere else:
docs/state/state-schema.md (path relative to the brain
root; walk up from wherever you are until you find brain.toml if you're in a leaf repo, then resolve
docs/state/state-schema.md from there). Read it before making any non-trivial edit. This command
is the workflow; state-schema.md is the ground truth.
When to use this
- You're about to hand-edit any
planning/state.json(adding/closing a block, appending acarryover[]entry, promoting a backlog item, fixing a validator warning). - You're renaming or restructuring block IDs (e.g. adopting the
<Prefix>.<Phase>.<Letter>convention) and need to know what else has to move in lockstep. - A planning command's instructions say "update
state.json" without repeating the mechanics — come here first.
The one rule that matters most: Authored vs Derived
state-schema.md's "Authored vs derived" table is the load-bearing distinction. Before touching any
field, know which bucket it's in:
| Bucket | Fields | You may hand-edit these |
|---|---|---|
| Authored (source of truth) | tracks[].blocks[] (id, title, status, depends_on, wave, note?, origin?, tasks?), backlog[] (HQ only), carryover[], HQ tiers[], epics[] (HQ only — plan field points at a roadmap's roadmap.md per /generate-roadmap's registration step), note (portfolio kind) |
Yes |
| Derived (a regenerated cache) | focus, brain repos[], brain cross_repo[], master-plan wave tables |
No — never hand-edit. Run mev emit-state --write instead |
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.
- 11d ago First seen · 123 lines · 0 tokens per session scan A aab0b3b98b4f
update-state is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,176 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 2026-10-26.
update-state compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| update-statebredmond1019/claude-sdk-rs | Command | 23 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |