Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Sassy-Dog/sassydog-skills/plugin install sassy-dogWrote 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/sassy-dog/sassydog-skills/whats-on-fire)<a href="https://agentmods.dev/skills/sassy-dog/sassydog-skills/whats-on-fire"><img src="https://agentmods.dev/badge/skills/sassy-dog/sassydog-skills/whats-on-fire/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/sassy-dog/sassydog-skills/whats-on-fire"><img src="https://agentmods.dev/badge/skills/sassy-dog/sassydog-skills/whats-on-fire.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 | $0.00203 | $0.06054 |
| Opus 5 | $0.00102 | $0.03027 |
| Sonnet 5 | $0.00041 | $0.01211 |
| Haiku 4.5 | $0.00020 | $0.00605 |
Grade A, and why
whats-on-fire 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 3d 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What's On Fire
One cross-product sweep of everything currently broken or stalled across a GitHub org, ranked, and routed to the repo that owns it.
This skill is read-only. It pulls, correlates, ranks, and reports. It NEVER files issues, changes Sentry status, or mutates anything — which is what makes it safe to run on a loop or a schedule.
Scope boundary. This decides which product deserves attention today. It deliberately does not
decide what to do inside that product — no tech-debt scan, no next-bet synthesis, no backlog
grooming. Those don't roll up meaningfully across a dozen products, and each repo's own survey-work
already does them with repo-specific knowledge this skill has no business duplicating. Report the
fire, name the repo, hand off.
1. Prerequisites
Run these probes. For each failure, label that surface skipped — <reason> in the output and
continue. Never abort the whole sweep on one missing precondition.
command -v gh && gh auth status
- GitHub CLI —
ghmissing entirely (cloud/CCR routine sessions ship without it) is the one probe failure that does NOT skip its surfaces: route the section 2B pulls through the GitHub-MCP fallback inreferences/cloud-fallback.mdinstead. Three parts of that surface have no MCP equivalent at all — Dependabot alerts, code-scanning alerts and secret-scanning alerts — and each is named on the sources line like any other skip:skipped — no gh CLI (Dependabot API unreachable)andSecurity scanning skipped — no MCP capability (code + secret scanning alerts unreachable).check-dispatch-recovery.sh(section 2A) also needsgh, and its fallback is in the same reference: query the runs capability scoped to the ONE workflow, never a repo-wide page. That distinction is not a detail — a repo-wide page truncates the evidence away and turns a verified-green control into a P0.ghpresent but unauthenticated stays an ordinary skip. - Sentry — probe by listing projects for the Sentry org; on error, skip both Sentry surfaces.
- Portfolio root — the local checkout directory (env
PORTFOLIO_ROOT, default~/Repos/sassy-dog). Only needed for the two blind spots that compare the org against local clones; if it's missing, skip those two rows and keep the rest.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed · +14 lines 25da42975153
- 4d ago Changed · +28 lines c6ec4d2752cb
- 12d ago First seen · 330 lines · 203 tokens per session scan A c328500f5513
whats-on-fire is a skill published in the GitHub repository Sassy-Dog/sassydog-skills (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 203 tokens to every session and 6,054 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
release-it
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
resolving-merge-conflicts
Use when a git merge or rebase reports conflicts and the operation is in progress.
git-investigate
Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.
analyze
Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots. Use whenever the user asks "how does X work", "map the Y flow", "what are the business rules for Z", "trace the auth path", "explore the codebase…