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 skills add tweag/tricorder --skill tricorder-mcpgit clone --depth 1 https://github.com/tweag/tricorderWrote 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/skills/tweag/tricorder/tricorder-mcp)<a href="https://agentmods.dev/skills/tweag/tricorder/tricorder-mcp"><img src="https://agentmods.dev/badge/skills/tweag/tricorder/tricorder-mcp/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/skills/tweag/tricorder/tricorder-mcp"><img src="https://agentmods.dev/badge/skills/tweag/tricorder/tricorder-mcp.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 | $0.00048 | $0.00580 |
| Opus 5.5 | $0.00019 | $0.00232 |
| Sonnet 5.5 | $0.00010 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
tricorder-mcp 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 17d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using the tricorder MCP Server
Use the mcp__plugin_tricorder-mcp_tricorder__* MCP tools for GHCi build
status, diagnostics, and test results in this project — don't run tricorder
as a Bash command; the MCP server already wraps it.
Tools
start— start the daemon (no-op if already running)stop/restart— stop/restart the daemon; passforce: trueto skip waiting on pending queriesstatus— current build status: diagnostics, errors, warnings. Passwait: trueto block until an in-progress build finishes,verbose: truefor full GHC message bodies, orexpand: Nto expand a single diagnostic. Returns JSON.test_results— output from the latest test run. Passwait: trueto block until the build/test cycle finishes, orfailed: trueto show only failing suites.source— Haskell source for one or more project or installed modules (e.g.Data.Map.StrictorData.Map.Strict#insert). Prefer this over downloading tarballs.eval_comments— eval comments and their evaluated results from the latest build. Passwait: trueto block until the build finishes. Returns JSON.log_contents/log_path— the daemon's log output, or the path to its log file.
All tools accept an optional projectRoot (defaults to the current working directory).
Workflow
- Edit source files.
- Call
statuswithwait: true— blocks until tricorder finishes recompiling. - If errors are shown, fix them and repeat.
- A clean result means the build is clean; configured test suites run automatically.
- Call
test_resultswithwait: true, failed: trueto see any test failures.
Notes
- The daemon is per-project, scoped by the resolved project directory.
statusauto-starts the daemon if it isn't running.- Do not run
cabal testmanually — the daemon manages test execution after each clean build. - If these MCP tools are unavailable, disconnected, or misbehave, and the
tricorderCLI is installed, fall back to running it directly via Bash (see thetricorderskill from thetricorderplugin, if installed).
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.
- 17d ago Changed bf76622b08f7
- 1mo ago First seen · 42 lines · 48 tokens per session scan A ebd18f6a2096
tricorder-mcp is a skill published in the GitHub repository tweag/tricorder (67 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 580 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
reproduce
Reproduces a paper's result, a claim, an artifact or a previous run with the target and success criterion frozen first, the canonical code path run before any substitute, exact inputs, environment, seeds and commands captured, and a verdict from a fixed set, reproduced, reproduced within tolerance, partially…
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
acceptance-checks
Turns the acceptance criteria a task states into executable checks and runs them against the finished outputs before delivering, rather than trusting that a correct-looking analysis satisfies them; rehearses the hidden condition when the grader scores unseen instances from a described family; treats a stated formula…