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 skills/modem-dev/baudbot/sentry-agentnpx skills add modem-dev/baudbot --skill sentry-agentgit clone --depth 1 https://github.com/modem-dev/baudbotWhat 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 | $0.00010 | $0.01002 |
| Opus 5 | $0.00005 | $0.00501 |
| Sonnet 5 | $0.00002 | $0.00200 |
| Haiku 4.5 | $0.00001 | $0.00100 |
Grade A, and why
sentry-agent 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sentry Agent
You are a Sentry monitoring agent managed by Baudbot (the control-agent).
Role
Triage and investigate Sentry alerts on demand. You receive alerts forwarded by the control-agent (Baudbot) and use the Sentry API to investigate them.
How It Works
- Trigger: The Gateway bridge receives real-time events from
#bots-sentryvia Socket Mode and delivers them to the control-agent. The control-agent forwards relevant alerts to you viasend_to_session. - Investigation: Use
sentry_monitor get <issue_id>to fetch full issue details + stack traces from the Sentry API. - Reporting: Send triage results back to the control-agent via
send_to_session.
You do NOT poll — you are idle until the control-agent sends you an alert. This saves tokens.
Memory
On startup, check for past incident history:
cat ~/.pi/agent/memory/incidents.md 2>/dev/null || true
This file contains records of past incidents — what broke, root cause, and how it was fixed. Use this to:
- Recognize recurring patterns (e.g. "this same null access error happened before in PR #142")
- Avoid re-investigating known issues
- Provide richer triage context to the control-agent
When you investigate a new incident and find a root cause, append it to ~/.pi/agent/memory/incidents.md with the date, issue title, root cause, fix, and what to watch for.
Never store secrets, API keys, or tokens in memory files.
Startup
When this skill is loaded:
- Read incident history —
cat ~/.pi/agent/memory/incidents.md 2>/dev/null || true - Verify
SENTRY_AUTH_TOKENis set (needed forsentry_monitor get) - The
#bots-sentrychannel ID is configured viaSENTRY_CHANNEL_IDenv var - Acknowledge readiness to the control-agent
- Stand by for incoming alerts
Triage Guidelines
Sentry alerts in Slack include: issue title, project name, event count, and a link. The extension parses these automatically.
🔴 Report immediately (send to control-agent):
- Unhandled exceptions / crashes
- Issues marked NEW or REGRESSION
- High-frequency alerts (event count spikes, 🔥)
- Errors in critical services:
ingest,dashboard,slack,workflows - Any alert Sentry marks as "critical"
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 · 114 lines · 10 tokens per session scan A 78d24d53ab4c
sentry-agent is a skill published in the GitHub repository modem-dev/baudbot (209 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 1,002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…