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.
npx skills add HigorAlves/orc --skill state-protocolgit clone --depth 1 https://github.com/HigorAlves/orcWrote 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/higoralves/orc/state-protocol)<a href="https://agentmods.dev/skills/higoralves/orc/state-protocol"><img src="https://agentmods.dev/badge/skills/higoralves/orc/state-protocol/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/higoralves/orc/state-protocol"><img src="https://agentmods.dev/badge/skills/higoralves/orc/state-protocol.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 | $0.00047 | $0.01855 |
| Opus 5.5 | $0.00019 | $0.00742 |
| Sonnet 5.5 | $0.00009 | $0.00371 |
| Haiku 4.5 | $0.00005 | $0.00186 |
Grade A, and why
state-protocol 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 yesterday.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
State Protocol
One schema, one writer, one startup sequence — defined here and only here. Commands defer to this skill instead of re-spelling state mechanics; bin/orc-state is the single writer, so the registry and every checkpoint's frontmatter cannot drift apart.
The one-writer rule
Never hand-write .orc/orc.json or a checkpoint's frontmatter — every mutation goes through orc-state (atomic jq writes; registry entry + checkpoint mirror updated by the same verb). The checkpoint body below the frontmatter is yours to write freely, except the ## Resume digest section, which only orc-state digest write - touches (it enforces the cap), and ## Auto-checkpoint, which only the PreCompact hook writes (orc-state checkpoint --auto — phase, slices, HEAD, dirty files; mechanical, so trust it over a stale digest for git state).
Register a session (the 2-line pattern every multi-phase command uses):
orc-state init --command <cmd> --total-phases <N> [--jira KEY] [--scope workspace --repos a,b] [--plan-file P]
Register state via
orc-state init; defer toorc-state-protocolfor schema and rules.
Then per phase boundary: orc-state phase set <n|done> [--label <word>], and rewrite the digest (below). On completion: orc-state status set completed.
Registry schema (.orc/orc.json, schema 1)
{ "schema": 1, "sessions": [{
"sessionId": "feat-142-notifs", // sanitized branch — THE key; one live session per branch
"command": "flow", "branch": "feat-142-notifs", "gitBranch": "feat/142-notifs",
"description": "≤120 chars", "status": "in_progress",
"phase": 5, "phaseLabel": "implement", "totalPhases": 9,
"jiraTicket": null, "planFile": null,
"linkedPRs": [{ "repo": "api", "number": 45, "url": "…", "stackId": null, "stackPosition": null, "stackedOn": null }],
"startedAt": "2026-08-20T14:03:00Z", "updatedAt": "2026-08-20T18:11:00Z",
"scope": "workspace", "repos": ["api", "ui"], "perRepoState": { "api": { "repoPath": "…", "branch": "…", "currentSlice": 0, "prUrl": null } }
}]}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed 1f30f8acf189
- 8d ago Changed 1d369326055a
- 14d ago Changed 63c7688dd086
- 17d ago Changed · +1 lines · -19 tokens per session 90086d3b57a2
- 1mo ago Changed 8d4f4b759f5e
- 2mo ago First seen · 99 lines · 66 tokens per session scan A 005e9d646375
state-protocol is a skill published in the GitHub repository HigorAlves/orc (7 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,855 once invoked, about $0.0002 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 2026-09-03.
state-protocol compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| state-protocolHigorAlves/orc | Skill | 7 | yesterday | MIT | A | 47 | Claude Code |
| clean-code-cppCassetteTapeCrackle/claude-starters | Skill | 1 | 4d ago | MIT | A | 42 | Claude Code |
| clean-code-coreCassetteTapeCrackle/claude-starters | Skill | 1 | 4d ago | MIT | A | 70 | Claude Code |
| agent-orchestrationCassetteTapeCrackle/claude-starters | Skill | 1 | 4d ago | MIT | A | 59 | Claude Code |
| clean-code-audioCassetteTapeCrackle/claude-starters | Skill | 1 | 4d ago | MIT | A | 52 | Claude Code |
| clean-code-rustCassetteTapeCrackle/claude-starters | Skill | 1 | 4d ago | MIT | A | 44 | Claude Code |
| clean-code-cCassetteTapeCrackle/claude-starters | Skill | 1 | 4d ago | MIT | A | 34 | Claude Code |