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 phase-loopgit 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/phase-loop)<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/phase-loop"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/phase-loop/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/phase-loop"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/phase-loop.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 | $0.00046 | $0.01121 |
| Opus 5.5 | $0.00018 | $0.00448 |
| Sonnet 5.5 | $0.00009 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
phase-loop 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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase loop and continuous operation
The coordinator owns the board and delegates research, design, implementation and verification. Run database ensure and read summary/profile before selecting a lifecycle. Existing approved work does not need a new concept interview just because the coordinator/plugin was installed or resumed.
New product or a genuinely new scope
- Bootstrap — use
coordinator-kit:bootstrapto preserve existing instructions/state and create only missing files. Record repository ownership, branch/deploy effects and permissions before building. A multi-repo workspace needs one lane/topology entry per checkout. - Repo analysis, when code exists — dispatched read-only agents map what is already there; consolidate a repo map before asking questions the code could answer. Link existing docs.
- Concept — ask unresolved product questions one at a time (vision, users, mechanism, UI/UX and relevant business constraints). Preserve raw answers; a dispatched agent synthesizes them into concept docs. The founder approves the concept before Objectives.
- Objectives — an agent drafts measurable priorities and defines how each will be validated. Do not defer the meaning of success until after implementation.
- Plan — an agent creates bounded tasks with goal, original source, dependencies, acceptance criteria, verification method, target environment, priority and next step. Record lasting architecture/cost choices as sourced decision records. The founder approves the plan before Execute. Existing explicit task/plan authorization counts; do not ask for the same permission again.
- Execute — follow
coordinator-kit:execute-loop: claim lane → premise check → build → independent verify → bounded fix cycles → final push gate → authorized push → CI/deployed outcome → record → next authorized task. Record intermediate stages without claiming the whole user goal is done. - Validate — a separate agent exercises each objective's defined method and writes evidence
to
docs/validation/. Prepare a reviewable launch if relevant; actual public/production release follows the project's authority rules. - Iterate — an agent proposes deltas from measured validation. The founder approves scope changes; resume at the affected phase rather than restarting the entire sequence.
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.
- 1mo ago Changed · -139 lines · -123 tokens per session 839cf2966ead
- 2mo ago Changed · +1 lines 1f91ed10d376
- 2mo ago First seen · 218 lines · 169 tokens per session scan A ee21e811e13d
phase-loop is a skill published in the GitHub repository nikolamin/claude-coordinator-kit (2 stars, last pushed 29d ago), licensed MIT. It adds 46 tokens to every session and 1,121 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 2026-08-31.
phase-loop compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| phase-loopnikolamin/claude-coordinator-kit | Skill | 2 | 29d ago | MIT | A | 46 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |