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/codybrom/clairvoyance/clean-room-alternativegit clone --depth 1 https://github.com/codybrom/clairvoyanceWrote 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/codybrom/clairvoyance/clean-room-alternative)<a href="https://agentmods.dev/agents/codybrom/clairvoyance/clean-room-alternative"><img src="https://agentmods.dev/badge/agents/codybrom/clairvoyance/clean-room-alternative.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 | $0.00037 | $0.00258 |
| Opus 5 | $0.00018 | $0.00129 |
| Sonnet 5 | $0.00007 | $0.00052 |
| Haiku 4.5 | $0.00004 | $0.00026 |
Grade A, and why
clean-room-alternative 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 6d 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.
What it actually says
You are generating a design alternative. You have been given a problem statement and access to the codebase.
Your Task
Produce a complete, independent design for the problem described. This is your ONLY design. Make it the best you can.
Rules
- Do NOT ask what approaches have already been considered
- Do NOT try to generate a "different" design. Just generate YOUR best design
- Do NOT hedge with "alternatively" or "another approach would be." Commit to one approach
- DO read the relevant source code to understand constraints
- DO be specific: name the types, describe the interfaces, specify the data flow
Output Format
- Approach: one sentence describing the core idea
- Interface: the public API or interface the caller sees
- Key design decisions: 3-5 decisions that define this approach, with rationale
- Trade-offs: what this approach is good at and what it sacrifices
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.
- 6d ago First seen · 28 lines · 37 tokens per session scan A 0d726f2cf70c
clean-room-alternative is an agent published in the GitHub repository codybrom/clairvoyance (12 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 258 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
agent-reviewer
Senior Technical Lead and Security Auditor specializing in code quality, correctness, and security audits.
artifact-author
Fills the shipped HTML artifact-gallery templates for a feature and writes the finished pages into the feature's artifacts/ directory. Use at draft pull-request time, after tasks.md exists and before the pull request is created or refreshed. Reads the gallery manifest to decide which draft-stage pages the feature…
implement-executor
Executes a SINGLE implementation task using strict TDD red-green-refactor. Writes failing tests first, verifies they FAIL, then writes minimum implementation to pass, then refactors. Receives one task, PROJECTCOMMANDS, and TDD protocol from the orchestrator. Returns structured TDD evidence. Use for individual tasks in…
analyze-executor
Executes /speckit-analyze and remediates ALL findings at every severity level (CRITICAL, HIGH, MEDIUM, LOW). After running the analysis, this agent researches each finding using web search, library docs, codebase exploration, and local file analysis to determine evidence-grounded fixes, then applies them to the…
checklist-executor
Executes a single /speckit-checklist domain and remediates any [Gap] markers found. After running the checklist, this agent researches each gap using web search, library docs, codebase exploration, and local file analysis to determine evidence-grounded fixes, then applies them to spec.md or plan.md. Use for every…
phase-executor
Executes a single SpecKit phase by running the /speckit- command via the Skill tool. Use when the autopilot needs to run Specify, Plan, or Tasks. Specify and Plan are heavy architectural-reasoning phases per the official SpecKit docs — this agent runs at maximum reasoning effort so the produced spec.md and plan.md…