Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tweag/tricordernpx agentmods add skills/tweag/tricorder/tricorder-cliWrote 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-cli)<a href="https://agentmods.dev/skills/tweag/tricorder/tricorder-cli"><img src="https://agentmods.dev/badge/skills/tweag/tricorder/tricorder-cli/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-cli"><img src="https://agentmods.dev/badge/skills/tweag/tricorder/tricorder-cli.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 | $0.00067 | $0.01827 |
| Opus 5.5 | $0.00027 | $0.00731 |
| Sonnet 5.5 | $0.00013 | $0.00365 |
| Haiku 4.5 | $0.00007 | $0.00183 |
Grade A, and why
tricorder-cli 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 7d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using tricorder to Check Build Status
tricorder is a daemon-based GHCi build monitor. It exposes build state over a Unix socket and outputs human-readable text by default, or JSON with --json for tool integration.
Commands
tricorder start— start the daemon (no-op if already running)tricorder stop— stop the daemon, waiting for pending queries before quittingtricorder stop --force-- stop the daemon, ignoring pending queriestricorder status— print current build state as texttricorder restart-- restart the daemon, waiting for pending queries before shutting downtricorder restart --force-- restart the daemon, ignoring pending queriestricorder status --wait— same, but blocks until the current build cycle finishestricorder status --json— output full build state as JSONtricorder status --wait --json— wait then output JSONtricorder status --verbose/-v— print full GHC message body under each diagnostictricorder status --expand <N>— print the summary line and full GHC message body for diagnostic #Ntricorder test-results— show full output from the latest test runtricorder test-results --failed— show output only from failed test suitestricorder test-results --wait— block until the current build cycle completes, then show resultstricorder source MODULE...— print Haskell source for one or more project or installed modules (e.g.tricorder source Data.Map.Strict)tricorder eval-comments— print eval comments and their evaluated results from the current build result.tricorder eval-comments --wait— print eval comments and their evaluated results, waiting for the current build to finish if it is in-progresstricorder eval-comments --json— print eval comments and their evaluated results as JSONtricorder eval-comments --wait --json— print eval comments and their evaluated results as JSON, waiting for the current build to finish if it is in-progresstricorder log— print the daemon log outputtricorder log --print-path— print the path to the log file instead of its contentstricorder ui— auto-refreshing terminal display (for humans)
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.
- 7d ago Changed 8e370609eef8
- 1mo ago Changed · -1 lines 11b0b8122543
- 1mo ago First seen · 211 lines · 67 tokens per session scan A f52cd47ad3b2
tricorder-cli is a skill published in the GitHub repository tweag/tricorder (65 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,827 once invoked, about $0.0003 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.
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…
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
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…