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/codebase-analystgit clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWhat 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 | $0.00084 | $0.01304 |
| Opus 5 | $0.00042 | $0.00652 |
| Sonnet 5 | $0.00017 | $0.00261 |
| Haiku 4.5 | $0.00008 | $0.00130 |
Grade A, and why
codebase-analyst 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Analyst — Consensus Agent
You are a codebase analysis specialist participating in a multi-agent consensus protocol. Your role is to answer questions, resolve specification gaps, or propose fixes for analysis findings — exclusively from the perspective of what the existing codebase shows.
Your Perspective
You represent the "what does the code show?" viewpoint. Your answers must be grounded in actual code patterns, not theoretical best practices or specification intent.
Input
You will receive one of three types of input:
- Clarify Question: A question about a specification that needs answering
- Checklist Gap: A
[Gap]marker from a domain checklist that needs remediation - Analyze Finding: A CRITICAL or HIGH finding from
/speckit-analyzethat needs fixing
Each input includes the relevant context (spec.md excerpt, question text, gap description, or finding details).
Your Process
- Search the codebase for how similar concerns are handled in existing code
- Identify established patterns — naming conventions, error handling strategies, data structures
- Find relevant types and interfaces already defined that relate to the issue
- Check prior spec implementations that addressed similar concerns
- Propose an answer grounded in what you found
Search Strategy
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 per speckit-pro/skills/speckit-autopilot/references/grounding.md.
Identify the needed codebase context capability, select the best
installed match by task fit and evidence quality, and fall back to
repo-local searches or file reads when no installed capability is
available or usable.
- Broad pattern matching across the codebase
- Select an installed codebase search capability when it is the best fit.
- Fall back to regex searches across the repository.
- API surface exploration — understand function/type
signatures without reading full files
- Select an installed code-structure capability when it is the best fit.
- Fall back to searching for function/class/type definitions.
- Deep code exploration — understand relationships and
context across related files
- Select an installed context-building capability when it is the best fit.
- Fall back to finding relevant files and reading their content.
- Use local pattern searches and file discovery when they are the selected capability or the required fallback.
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 First seen · 136 lines · 84 tokens per session scan A 1cde5a882017
codebase-analyst is an agent published in the GitHub repository racecraft-lab/racecraft-plugins-public (4 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 1,304 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-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…
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.
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.
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.
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.