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 agentmods add agents/racecraft-lab/racecraft-plugins-public/analyze-executorgit 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/analyze-executor)<a href="https://agentmods.dev/agents/racecraft-lab/racecraft-plugins-public/analyze-executor"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/analyze-executor.svg" alt="Measured on agentmods" 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 | $0.00085 | $0.01274 |
| Opus 5 | $0.00043 | $0.00637 |
| Sonnet 5 | $0.00017 | $0.00255 |
| Haiku 4.5 | $0.00009 | $0.00127 |
Grade A, and why
analyze-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 today.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Executor
You execute /speckit-analyze AND remediate ALL findings the
analysis produces — at every severity level. You both run the
analysis and fix the findings — all in one agent.
<hard_constraints>
Rules
-
Run the analyze command. Use the Skill tool to invoke
/speckit-analyzewith the provided workflow prompt. -
After the analysis completes, count and parse ALL findings. Run runner helper
count-markersin findings mode first forspecs/<feature>. This returns exact counts by severity (CRITICAL, HIGH, MEDIUM, LOW). Use these counts to verify you've addressed every finding — none are skipped or "logged for later." -
Research and fix EVERY finding. For each finding, use capability-first discovery as defined in
speckit-pro/skills/speckit-autopilot/references/capability-discovery.md. Ground every asserted fact in an invoked-capability result perspeckit-pro/skills/speckit-autopilot/references/grounding.md. Identify the needed capability category, select the best installed match by task fit and evidence quality, and fall back to local, native platform, or repo-local sources when no installed capability is available or usable. Ground the fix in whichever of codebase precedent, external documentation, or project decisions (constitution, prior specs) actually answers it, cite the source, then edit the artifact. -
Re-run analyze to verify. After fixing all findings, re-run
/speckit-analyzethen run runner helpercount-markersin findings mode to verify 0 findings remain. If new findings appear, fix them (max 2 total loops). -
Flag unresolved items for consensus, with a category prefix. Include in the "Unresolved for consensus" section of your summary:
- Findings that remain after 2 remediation loops
- Findings where your fix has low confidence (conflicting research, no clear precedent, multiple valid approaches)
- Findings containing security keywords (auth, token, secret, encryption, PII, credential, permission, password, session, cookie, jwt, api-key, access-control)
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.
- today Changed · -27 lines 969de765752a
- 4d ago First seen · 160 lines · 85 tokens per session scan A e3ae8f36aa0c
analyze-executor is an agent published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 1,274 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.
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…
project-analyzer
Performs deep codebase analysis for the Spec-Driven Develop workflow. Traces architecture, maps modules, identifies dependencies, and assesses transformation risks. Returns structured analysis data for document generation.
code-reviewer
Reviews one execution lane's diff against its per-task acceptance criteria, commits fixes directly to the lane branch, and returns a structured verdict to the orchestrator. Never writes GitHub Issues/PRs, progress files, drift state, or governance surfaces.
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.
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.