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 tslateman/duet --skill automagic-problem-discoverygit clone --depth 1 https://github.com/tslateman/duetWrote 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/tslateman/duet/automagic-problem-discovery)<a href="https://agentmods.dev/skills/tslateman/duet/automagic-problem-discovery"><img src="https://agentmods.dev/badge/skills/tslateman/duet/automagic-problem-discovery.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.02088 |
| Opus 5 | $0.00037 | $0.01044 |
| Sonnet 5 | $0.00015 | $0.00418 |
| Haiku 4.5 | $0.00007 | $0.00209 |
Grade A, and why
automagic-problem-discovery 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 7d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automagic Problem Discovery
Overview
Most automation gets built for the friction someone noticed. This skill hunts the friction they stopped noticing: the manual step repeated so often it no longer registers as a cost.
One pass. Census, audit, pick one problem, build the fix, verify, report, log. The user leaves with a working tool, not a list of suggestions, and the ledger entry that stops the next run from rediscovering it.
Scope and autonomy
Never read credential stores, private keys, secret values, personal communications, or any directory and channel the user excluded. Ask before touching anything ambiguous.
Everything else is fair game: shell history, logs, cron and launchd jobs, scripts, git history, PR and CI state, prompt history, session transcripts, project layout, task runners.
When this skill starts a recurring loop, ask once before the first cycle: "discover and propose only" or "build and execute". The answer holds for the whole loop. A single interactive invocation defaults to build and execute, inside the Step 6 gate.
Step 1: Census what already exists
Before hunting new friction, read the estate:
- The automation home: wherever this workspace's cron, launchd, or CI automations live, and whatever status tooling watches them.
- The discovery ledger:
discovery-ledger.mdin the automation home, recording what past runs built, held, and rejected. - Prior discovery artifacts: earlier audits, velocity analyses, and proposal reports in session transcripts beat re-deriving from scratch.
- In-flight work: open tickets and branches. Friction that a human is already fixing is a rejection, not a target.
- The graveyard: tooling that was built and then deleted is the strongest signal in the corpus, and the most dangerous. Find the removal reason before building in that space. If the reason is unstated, ask, or build a strictly weaker posture (report-only, different home) and say so in the report.
Done when the run can name what already covers, addresses, or previously died in each candidate space.
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.
- 7d ago First seen · 147 lines · 74 tokens per session scan A 1c6a2db092c0
automagic-problem-discovery is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 11d ago), licensed MIT. It adds 74 tokens to every session and 2,088 once invoked, about $0.0004 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
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.
grill
Interrogate a plan or decision one question at a time before capture, keeping a decision-plus-rationale ledger, then route to the right capture skill.
architect
Answer build-or-adopt honestly, then design one committed architecture from your own understanding of the problem — driven by ranked quality attributes, stress-tested against the field and against change, proven by a walking skeleton, its consequences confirmed by the user, committed to ARCHITECTURE.md. A command the…
designer
Settle the look before the pixels — audience and context first, then the base and the delta, taste settled by looking at real states, accessibility as the floor, one design language committed to DESIGN.md as tokens with roles. A command the user types, for work with an interface someone will see; standalone, no other…
setup-working-genius
Per-repo configuration — pin the work-file directory, verify commands, and issue tracking, seed the project docs, and leave the pointer that tells every future session this project works this way.