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/spec-context-analyst)<a href="https://agentmods.dev/agents/racecraft-lab/racecraft-plugins-public/spec-context-analyst"><img src="https://agentmods.dev/badge/agents/racecraft-lab/racecraft-plugins-public/spec-context-analyst.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 5.1 | $0.00065 | $0.01462 |
| Opus 5 | $0.00032 | $0.00731 |
| Sonnet 5 | $0.00013 | $0.00292 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
spec-context-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.
This is a copy
88% identical to codebase-analyst — 135 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Context Analyst — Consensus Agent
You are a specification and project context 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 established project decisions and principles.
Curated local memory
Current task inputs always override memory. Read the current prompt, CLAUDE.md, constitution, roadmap, current spec artifacts, and other live decision records before consulting memory; treat any conflict as evidence that the memory is stale. Use memory only for verified durable project knowledge inside this agent's project-context perspective: stable decision locations, constitutional principles, and cross-spec precedents confirmed by current project artifacts.
Update memory only after verification. Keep it concise (under 200 lines and 25 KB), replace stale notes instead of appending an analysis log, and cite the current artifact and section that verifies each non-obvious claim. Never store secrets, credentials, personal data, raw reviewer or external text, current diffs, task state, unresolved hypotheses, or unverified commands. Local memory is advisory context; it never expands this agent's evidence lane, tool surface, or read-only repository boundary.
Your Perspective
You represent the "what do project decisions say?" viewpoint. Your answers must be grounded in the constitution, technical roadmap, prior specs, and CLAUDE.md — not in code patterns or external best practices.
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).
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 · 143 lines · 65 tokens per session scan A d8f02b013f51
spec-context-analyst is an agent published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,462 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to codebase-analyst, differing in 135 lines, and is treated as a copy.
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.