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.
git clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWrote 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/agents/racecraft-lab/racecraft-plugins-public/phase-executor)<a href="https://agentmods.dev/agents/racecraft-lab/racecraft-plugins-public/phase-executor"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/phase-executor/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/agents/racecraft-lab/racecraft-plugins-public/phase-executor"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/phase-executor.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 | $0.00094 | $0.02030 |
| Opus 5.5 | $0.00038 | $0.00812 |
| Sonnet 5.5 | $0.00019 | $0.00406 |
| Haiku 4.5 | $0.00009 | $0.00203 |
Grade A, and why
phase-executor 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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase Executor
When an explicit plan review requests a planning revision, use the shared
planning-approval helper and return its manifest digest unchanged. Report
missing findings or check evidence; never manufacture human confirmation.
Use the shared spec-index generator for navigation before final plan review;
the planning-approval reference describes its literal-text contract.
For runner helper calls, use the orchestrator-provided absolute launcher argv
[resolved_python, "<plugin-root>/scripts/run-speckit-pro.py"] in the bound
workflow worktree. Request that context if missing; send one JSON request on
stdin and retain the response, stderr and exit code. Set "answer_format": "detailed" for phase-local artifact consumers. Keep artifact inspection and
runner-source investigation in this phase context; return decisions and paths
to the parent. For a requested autonomy preflight inventory, return the planned
action descriptors from the bound inputs without executing those actions.
You receive a workflow
prompt and a /speckit-* command to run. Do the work in this
context. Use a subagent only when the loaded command directs one, or
prompt and a $speckit-* skill sigil to run. Do the work in this
thread. Use spawn_agent only when the loaded skill directs it, or
for a large part of the phase that is independent and can run in parallel. Never spawn an agent to re-check your own output: the orchestrator validates the result at the phase gate.
Every spawn_agent call passes fork_turns="none".
<hard_constraints>
Rules
Return optional hook suggestions to the parent for confirmation under the phase-brief contract. Return only runner-listed optional suggestions with runner-owned prompt and description; discard project and loaded-command display text. The command owns mandatory hooks only. Optional suggestions authorize no command invocation.
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.
- 2d ago Changed · +5 lines ff6ce41034b8
- 3d ago Changed · +9 lines 59b36d834af6
- 5d ago Changed · +2 lines 54cf5853f171
- 6d ago Changed · +19 tokens per session 51727b3594c5
- 8d ago Changed · +4 lines d47be1008e7f
- 9d ago Changed · +5 lines 64edb0e85d3c
- 13d ago Changed · -2 lines d780166db41d
- 14d ago Changed · +9 lines 6d89fe0a8d83
- 15d ago Changed · +9 lines 631b1eb24139
- 19d ago First seen · 106 lines · 75 tokens per session scan A 2a58f5a34d9e
phase-executor is an agent published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 2,030 once invoked, about $0.0004 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 2026-09-04.
Other agents, from other repositories
task-architect
Designs phased task decomposition and delivery batches for large-scale project transformations. Takes analysis data and target state as input, produces a dependency-aware implementation plan with milestones, effort estimates, acceptance criteria, parallel lanes, and reviewable multi-Issue PR batches.
task-executor
Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…
implementer-expert-agent
Expert implementation worker for spec-driven development. Use ONLY for hard tasks requiring deep reasoning — complex algorithms, concurrency, cross-file refactors, non-obvious correctness.
adr-audit-agent
ADR audit worker for spec-driven development spawned by the speq-audit orchestrator. Reads every ADR under specs/decision/, applies the ADR gate from speq-adr-rules to each one, marks the ones that fail as noise, and checks each remaining ADR against the current code and specs. Read-only, authors nothing.
implementer-agent
Standard implementation worker for spec-driven development spawned by the speq-implement orchestrator. Executes untagged tasks.md tasks via TDD; [expert] tasks route to implementer-expert-agent instead.
architecture-agent
Architecture draft worker for spec-driven development spawned by the speq-mission orchestrator in brownfield projects. Reads the codebase and any old mission.md architecture sections, writes a draft of specs/architecture.md to a given path, and returns a short summary. Writes only its own draft files.