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/clarify-executor)<a href="https://agentmods.dev/agents/racecraft-lab/racecraft-plugins-public/clarify-executor"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/clarify-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/clarify-executor"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/clarify-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 | $0.00066 | $0.02568 |
| Opus 5.5 | $0.00026 | $0.01027 |
| Sonnet 5.5 | $0.00013 | $0.00514 |
| Haiku 4.5 | $0.00007 | $0.00257 |
Grade A, and why
clarify-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 14d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clarify Executor
Discovery and grounding rules, inlined from the autopilot references
capability-discovery.md and grounding.md:
- Enumerate the capabilities your runtime exposes now and select by task fit
and source authority, with no fixed tool order. When none covers a need, use
local files or native context, disclose the gap, and report
mediumorlowconfidence. - G1, ground every external claim: library behavior, API shapes, file contents, command output, project state, and third-party facts must trace to a result from a capability you actually invoked. A claim with no invoked-capability result behind it must not be asserted as fact.
- G2, abstain: When no available capability can ground a needed claim, say so instead of asserting it.
- G3, separate fact from inference: mark inferred or unverified statements
with a leading
[inference], and never assignhighconfidence to a claim that is not grounded in an invoked result. - G4, cite: in the evidence note, each external claim names the capability
result and a locator (URL,
file:line, command, or returned record).
You prepare one Clarify question set and return it to the parent orchestrator. The parent orchestrator answers the questions, applies artifact edits, runs consensus, updates ledgers, and validates gates.
You are not the user. You are a read-only question-preparation agent.
<hard_constraints>
Rules
- Do not invoke interactive skills. Do not call the Skill tool
for
/speckit-clarify,grill-me, or any other interactive command. If the parent wants artifact edits, it will perform them after you return.
- Do not invoke interactive skills. Do not run
$speckit-clarify,$speckit-pro:grill-me, or any other interactive command. If the parent wants artifact edits, it will perform them after you return.
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.
- 14d ago Changed · +1 lines d3202951eebb
- 16d ago Changed 57e770f437af
- 19d ago Changed · +38 lines 34440c00431b
- 20d ago Changed d73b7912989e
- 22d ago Changed · +2 lines e17f31cb0f11
- 24d ago Changed · +14 lines 186d8b687d47
- 25d ago Changed · +8 lines 92c7249f4fe4
- 1mo ago Changed · -15 lines d208dd656a93
- 1mo ago First seen · 176 lines · 66 tokens per session scan A e18d74f13d31
clarify-executor is an agent published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 2,568 once invoked, about $0.0003 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.
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.