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/.agents/skills/derive-state-safely/SKILL.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/skills/bredmond1019/claude-sdk-rs/derive-state-safely)<a href="https://agentmods.dev/skills/bredmond1019/claude-sdk-rs/derive-state-safely"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/derive-state-safely/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/skills/bredmond1019/claude-sdk-rs/derive-state-safely"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/derive-state-safely.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 | $0.00172 | $0.03569 |
| Opus 5.5 | $0.00069 | $0.01428 |
| Sonnet 5.5 | $0.00034 | $0.00714 |
| Haiku 4.5 | $0.00017 | $0.00357 |
Grade A, and why
derive-state-safely 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running the state writers safely
Paths below are relative to the brain root — the directory containing
brain.toml, found by walking up from wherever you are. This skill is synced into every repo, so a repo-relative link would be wrong in most of them.
emit-state --write is the fleet's destructive routine command. It rewrites generated surfaces
across every repo from authored state. Run it with a stale binary and it rewrites them in an
older format — that is a silent regression, not an error.
It is not the only command that runs it. Every authored-state write verb re-runs
emit-state --write internally on success, so everything in this skill applies to all of them.
The hazard is the write, not the command name you typed:
| Command | Shape | Re-runs emit-state --write |
|---|---|---|
mev emit-state --write |
the write itself | — |
mev set-block-status <repo:id> <status> --write |
dry-run by default | yes |
mev defer-epic · resume-epic · complete-epic · sync-epics (--write) |
dry-run by default | yes |
mev close-operator-gate <slug> --exit-verified |
verified-or-refused, no dry-run | yes |
mev approve <slug> --digest <d> · mev reject <slug> |
digest-bound | yes |
./scripts/emit_state_write.sh · validate_brain.sh · routine.sh |
wrappers | yes |
So mev set-block-status mev:MV.10.A closed --write against a stale binary regresses boards
fleet-wide exactly as a bare emit-state --write would. There is no "small" writer — the
one-block verb and the whole-corpus command have the same blast radius on derived surfaces.
mev carryover, frontier, lanes, conformance and every validate-* verb are read-only and
exempt. mev carryover --dispose (MV.ticket.carryover-dispose) is not — add it to the table
above when it ships.
Step 1 — Rebuild first. This is not optional.
mev conformance --check toolchain-freshness
Drifted output names the two commits and says "rebuild before any --write run". Then:
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 · 212 lines · 172 tokens per session scan A 058eaae817a6
derive-state-safely is a skill published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 172 tokens to every session and 3,569 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-26.
derive-state-safely compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| derive-state-safelybredmond1019/claude-sdk-rs | Skill | 23 | 1mo ago | Apache-2.0 | A | 172 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |