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 nikolamin/claude-coordinator-kit --skill coordination-stategit clone --depth 1 https://github.com/nikolamin/claude-coordinator-kitWrote 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/nikolamin/claude-coordinator-kit/coordination-state)<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/coordination-state"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/coordination-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/skills/nikolamin/claude-coordinator-kit/coordination-state"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/coordination-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 | $0.00052 | $0.02004 |
| Opus 5.5 | $0.00021 | $0.00802 |
| Sonnet 5.5 | $0.00010 | $0.00401 |
| Haiku 4.5 | $0.00005 | $0.00200 |
Grade A, and why
coordination-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 28d 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.
Database-backed coordination
The canonical record is <workspace>/.coordinator/coord.db, created by the bundled
Python CLI. Python 3.9+ with sqlite3 is required; no pip packages or
server are needed. This replaces writable STATE.md, plan.md, decisions, question queues, operating
profiles, repo maps and coordination logs. Concept/design/validation artifacts and behavioral
instructions remain files. Retired filenames contain compatibility pointers, not parallel state.
Use the script's resolved absolute path and explicit workspace root (which may contain several
Git repos). The plugin's SessionStart hook runs migration on startup/resume in recognized
coordinator workspaces when supported, enabled and trusted. Codex requires user trust for bundled
hooks. If hooks are untrusted, disabled, unavailable, or the workspace is new, bootstrap
must run the same ensure --init command before coordination. Never claim migration succeeded
from plugin installation alone.
python3 <plugin-root>/scripts/coord.py --root <workspace> ensure --init
python3 <plugin-root>/scripts/coord.py --root <workspace> summary
python3 <plugin-root>/scripts/coord.py --root <workspace> review list
First-run migration
ensure snapshots recognized legacy coordination files and databases, imports original bytes
and searchable sections in a transaction, checks integrity and archive bytes, then replaces
Markdown sources with pointers. It is idempotent and resumes interrupted cutover. Every original
is recoverable with source list / source show ID --output NEW_PATH, as well as from its
.coordinator/migrations/ archive. Existing SQLite stores are imported via consistent snapshots;
the originals are preserved with .MIGRATED.md pointers and an explicit integration-review item.
Repoint their old readers/writers before treating the new database as the sole live backend.
Recognizable checklist/legacy DB records are imported conservatively. Uncertain statuses, free
prose, holds/lifts, questions, operating configuration and stop notes require coordinator
reconciliation, not guessed approvals. Use review show SECTION_ID, create/update canonical
records carrying original requirements/provenance, then review resolve SECTION_ID --note TEXT --refs RECORD_ID .... Use --historical only after verifying that a section has no remaining
operational content. Do not dismiss an active constraint simply to clear the queue. Imported
needs_review records also need a deliberate status update. summary.ready_for_dispatch must
be true before dispatch; it certifies migration readiness, not authorization to run every task.
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.
- 28d ago Changed · +10 lines f8c02d67f0f6
- 1mo ago Changed · +23 lines 51ca85ab2196
- 1mo ago First seen · 90 lines · 52 tokens per session scan A 1c94966c5fb6
coordination-state is a skill published in the GitHub repository nikolamin/claude-coordinator-kit (2 stars, last pushed 29d ago), licensed MIT. It adds 52 tokens to every session and 2,004 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 2026-09-26.
coordination-state compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| coordination-statenikolamin/claude-coordinator-kit | Skill | 2 | 29d ago | MIT | A | 52 | Claude Code |
| create-prprisma/orm | Skill | 48k | today | Apache-2.0 | A | 48 | Claude Code, Codex |
| schema-explorationlangchain-ai/deepagents | Skill | 31k | today | MIT | A | 57 | Claude Code, Codex |
| atlas-mssqlariga/atlas | Skill | 8.8k | 2d ago | Apache-2.0 | A | 163 | Claude Code |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | today | MIT | A | 115 | Claude Code, Codex |
| nornicdb-cypher-queriesorneryd/NornicDB | Skill | 924 | today | MIT | A | 79 | Claude Code, Codex |
| volcengine-rds-postgresqlbytedance/agentkit-samples | Skill | 484 | yesterday | Apache-2.0 | A | 63 | Claude Code, Codex |