Marin is an open-source research program, software platform, and community for developing foundation models such as large language models. Researchers use it for data preparation, tokenization, pretraining, posttraining, evaluation, and related experiments, including work on audio-text, DNA, and protein models. The catalogue entries are add-ons that support workflows around Marin.
Borrowing it
Nothing to install: this file belongs to marin-community/marin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marin-community/marin/main/.agents/skills/triage-canary/SKILL.mdgit clone --depth 1 https://github.com/marin-community/marinWrote 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/marin-community/marin/triage-canary)<a href="https://agentmods.dev/skills/marin-community/marin/triage-canary"><img src="https://agentmods.dev/badge/skills/marin-community/marin/triage-canary/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/marin-community/marin/triage-canary"><img src="https://agentmods.dev/badge/skills/marin-community/marin/triage-canary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00825 |
| Opus 5 | $0.00013 | $0.00413 |
| Sonnet 5 | $0.00005 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
triage-canary scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Triage Canary
Triage a failed canary ferry run. Diagnose root cause, file a GitHub issue, write a Slack summary. Diagnosis and reporting only — no code changes, no PRs.
CI invocation context
The composite action includes these non-secret values in the prompt. Use the prompt values directly instead of inspecting the process environment. Matching environment variables remain available to commands invoked during triage.
| Variable | Description |
|---|---|
CANARY_LANE |
gpu (CoreWeave) or tpu (GCP) |
CANARY_JOB_ID |
Iris job ID |
CANARY_RUN_ID |
W&B run ID |
IRIS_CONFIG |
Path to Iris cluster config |
IRIS_NAMESPACE |
Kubernetes namespace (CW only) |
WANDB_ENTITY |
W&B entity |
WANDB_PROJECT |
W&B project |
GHA_RUN_URL |
Full URL to the GitHub Actions run |
Steps
1. Gather diagnostics
The cluster is still live. Collect signal now — it will be torn down after you.
- Iris job state via
.venv/bin/iris --config=$IRIS_CONFIG job list - GPU lane: you have kubectl at
~/.kube/coreweave-iris, namespace$IRIS_NAMESPACE(defaults toiris-ci— the canary shares this namespace with PR CI). Get pod status, controller logs, task pod logs, warning events, pod describe. Filter byiris.job_id=<CANARY_JOB_ID with '/' replaced by '.'>so you only see this canary's pods, not co-tenant CI pods. Example:kubectl -n iris-ci get pods -l iris.job_id=runner.iris-run-job-abc123. - TPU lane: use
iris process logsandiris job list. - Re-run
scripts/ci/validate_canary_metrics.pyif you need the validation output.
2. Identify root cause
Classify into one of: infra/scheduling, training crash, metric regression, controller bug, data/storage.
Use hypothesis-driven diagnosis: state hypothesis, gather evidence, narrow. Attempt to reproduce the issue locally and minimally. Triple check that you're narrowing down on the same issue as the one that actually broke the canary.
3. File a GitHub issue
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.
- 13d ago First seen · 78 lines · 25 tokens per session scan A 6e5928c9996c
triage-canary is a skill published in the GitHub repository marin-community/marin (3,607 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 825 once invoked, about $0.0001 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 skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.