agentmods.dev

sentry-brief

sentry-brief is a skill for Claude Code, Codex from CassioRoos/godfly-skills. It costs 57 tokens per session (333 once invoked), scanned A, original, MIT.

A format for turning an alert payload into a short incident brief. It states who is affected, ranks possible causes, gives checks that could disprove them, and separates immediate containment from the eventual fix.

In plain words
What is it for?
It is for responding to pages, triaging incidents, handing incidents to another responder, and choosing the next diagnostic step.
Why use it?
It turns raw monitoring data into a clear next decision while keeping missing information and uncertain causes explicit.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 1repo yesterday A scan 57 tokens original MIT

Good fit It is for responding to pages, triaging incidents, handing incidents to another responder, and choosing the next diagnostic step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cassioroos/godfly-skills/sentry-brief-v3
View source ↗ CassioRoos/godfly-skills
Install

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.

Any agent
npx skills add CassioRoos/godfly-skills --skill sentry-brief-v3
Clone the repo
git clone --depth 1 https://github.com/CassioRoos/godfly-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sentry-brief

README.md
[![agentmods](https://agentmods.dev/badge/skills/cassioroos/godfly-skills/sentry-brief-v3/github.svg)](https://agentmods.dev/skills/cassioroos/godfly-skills/sentry-brief-v3)
Your own site
<a href="https://agentmods.dev/skills/cassioroos/godfly-skills/sentry-brief-v3"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/sentry-brief-v3/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.

agentmods 80×15 button for sentry-brief

Your own site · 80×15
<a href="https://agentmods.dev/skills/cassioroos/godfly-skills/sentry-brief-v3"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/sentry-brief-v3.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 333 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.00333
Opus 5.5 $0.00023 $0.00133
Sonnet 5.5 $0.00011 $0.00067
Haiku 4.5 $0.00006 $0.00033

Measured 2mo ago against content hash 43fdb27ecc5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sentry-brief 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 2mo 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.

evals/gauntlet/analysis-axis/sentry-brief-v3-SKILL.md · 38 lines

What it actually says

Sentry Brief

An alert is data. A brief is a decision. Convert one into the other in under a screen.

Rules

  1. Blast radius before cause. Name who is currently harmed and how, before theorising about mechanism.
  2. Three discriminating checks. Every suspected cause ships with the check that would falsify it. A check that every hypothesis passes is not a check.
  3. Containment is separate from fix. State the action that stops harm now, even if it is ugly, and mark it as containment.
  4. Unknowns stay unknown. If the payload does not contain it, write "not in payload". Never infer a customer count, a region, or a dollar figure.
  5. One screen. If the brief does not fit on one screen it is not a brief.

Output

IMPACT   -> who is harmed, right now, and how
SUSPECTS -> ranked causes, each with its discriminating check
CONTAIN  -> the action that stops harm now
NEXT     -> the single next diagnostic step and its owner
UNKNOWN  -> what the payload does not tell us
Changes

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.

  1. 2mo ago First seen · 38 lines · 57 tokens per session scan A 43fdb27ecc5b

Subscribe to this mod's changes

sentry-brief is a skill published in the GitHub repository CassioRoos/godfly-skills (1 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 333 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 2026-09-04.

Claude CodeCode reviewDebuggingDevOps and cloudadversarial-reviewagent-skillsclaude-skillscodex-cli
Related

sentry-brief compared with skills from other repositories

sentry-brief next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sentry-briefCassioRoos/godfly-skillsSkill1yesterdayMITA57Claude Code, Codex
challenge-resolveBorda/AI-RigSkill31yesterdayApache-2.0A74Claude Code, Codex
code-remediateBorda/AI-RigSkill31yesterdayApache-2.0A39Claude Code, Codex
auditoliver-kriska/claude-elixir-phoenixSkill573yesterdayMITA35Claude Code
ai-slop-cleanervibeeval/vibecosystemSkill5392d agoMITA50Claude Code, Codex
code-review-webrampstackco/claude-skillsSkill1.0k11d agoMITA121Claude Code
java-code-reviewsivaprasadreddy/sivalabs-agent-skillsSkill1947d agoMITA64Claude Code