phase-runner

A draft skill for taking one delivery task from a work board through claiming, test-driven development, verification, and handoff. TDD means writing and running a failing test before implementing the code.

In plain words
What is it for?
Use it when taking the next ready task, working on a specific task ID, or following the repository's delivery-board protocol.
Why use it?
It defines a fixed process for choosing tasks, limiting changes to the contract, and proving the result works before handoff.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/binary16labs/prime-silo/phase-runner
Any agent
npx skills add binary16labs/prime-silo --skill phase-runner
Clone the repo
git clone --depth 1 https://github.com/binary16labs/prime-silo

Made for: Claude Code, Codex.

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 507 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00082 $0.00507
Opus 5 $0.00041 $0.00253
Sonnet 5 $0.00016 $0.00101
Haiku 4.5 $0.00008 $0.00051

Measured 2d ago against content hash 9f42908c5249, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phase-runner 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 2d 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.

.claude/skills/phase-runner/SKILL.md · 26 lines

What it actually says

Phase runner (draft — manual protocol until W1/W2 land)

  1. Read the protocol once: delivery/README.md. It is binding; this skill is its checklist.
  2. Select: open delivery/board/BOARD.md, take the TOPMOST item in READY. Never choose.
  3. Claim: move its line to CLAIMED (· <agent> · <ISO date>), append a claimed line to delivery/board/LOG.md, commit chore(delivery): claim <ID> BEFORE working.
  4. Sandbox: git worktree add .worktrees/<ID> -b feat/<ID> main (contract sandbox: worktree). Work only inside it. Never restart services a live run depends on.
  5. Read ONLY your contract (delivery/tasks/<ID>.md). Insufficient contract = log blocked: contract insufficient — <missing> and stop. Never improvise scope.
  6. TDD, in order: failing test (run it, observe red, commit) → implement → green → refactor. Name tests after the contract's Scenario: lines. Respect the allowlist and budget.
  7. Verify: run the contract's verify command until exit 0 from a clean tree. Lint/format touched files. Validate contracts changed: node scripts/gates/w0.mjs.
  8. Hand off: move the board line to VERIFY + append ready-for-verify to LOG (honest deviations included), commit on main. You may NOT move your own task to DONE — a fresh clean-checkout session with a distinct identity re-runs the gate (README rule 7).
  9. Blocked twice = stop. Append blocked with the exact error and what you tried.

Log format: <ISO-ts> | <task-id> | <event> | <agent> | <note> — append-only, never edit history.

Changes

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.

  1. 2d ago First seen · 26 lines · 82 tokens per session scan A 9f42908c5249

Subscribe to this mod's changes

phase-runner is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 9d ago), licensed MIT. It adds 82 tokens to every session and 507 once invoked, about $0.0004 per session on Opus 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.