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 skills add ckorhonen/swe-skills --skill observability-gap-huntgit clone --depth 1 https://github.com/ckorhonen/swe-skillsWrote 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/ckorhonen/swe-skills/observability-gap-hunt)<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/observability-gap-hunt"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/observability-gap-hunt/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/ckorhonen/swe-skills/observability-gap-hunt"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/observability-gap-hunt.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 | $0.00109 | $0.01366 |
| Opus 5 | $0.00055 | $0.00683 |
| Sonnet 5 | $0.00022 | $0.00273 |
| Haiku 4.5 | $0.00011 | $0.00137 |
Grade A, and why
swe:observability-gap-hunt 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 12d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE Observability Gap Hunt
What This Skill Does
Use this skill to find observability blind spots in a repository and turn them into a small, reviewable backlog.
The job is to identify where a service or code path lacks enough signal to be operated confidently, then rank the smallest improvements that would materially improve detection, diagnosis, or alerting.
This is not a performance tuning skill. The focus is telemetry coverage and operational visibility.
When To Use
Use this skill when the user wants to:
- audit logs, metrics, traces, alerts, or dashboards for gaps
- check whether important workflows are observable enough to operate safely
- find missing deployment-linked telemetry or runbook coverage
- run a recurring observability review over time
Do Not Use
Do not use this skill for:
- live incident response or active root-cause analysis
- generic latency, throughput, or performance optimization
- broad application code review with no observability goal
- redesigning the entire monitoring stack
- replacing existing observability tooling without repository evidence
Inputs To Confirm
Confirm or infer:
- repository, service, or package scope
- whether the user wants a report-only pass or a small backlog of follow-up work
- which observability systems are available locally or in connected tools
- whether recent incidents, deploys, or operational pain points matter
- any no-touch areas or known noisy surfaces
If scope is unclear, narrow it to the smallest service or package set that still fits the request.
Tooling Stance
This skill is tool agnostic.
Use the strongest available evidence sources, such as:
- application code and middleware
- logging helpers and structured log patterns
- metrics emitters, counters, timers, and labels
- tracing spans and context propagation
- alert rules and SLO definitions
- dashboard or panel configuration
- deploy manifests, release hooks, or health checks
- runbooks or operational docs tied to the service
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.
- 12d ago First seen · 215 lines · 109 tokens per session scan A fe66b89f75ab
swe:observability-gap-hunt is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,366 once invoked, about $0.0005 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.