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 paultyng/skill-issue --skill discover-patternsgit clone --depth 1 https://github.com/paultyng/skill-issueWrote 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/paultyng/skill-issue/discover-patterns)<a href="https://agentmods.dev/skills/paultyng/skill-issue/discover-patterns"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/discover-patterns/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/paultyng/skill-issue/discover-patterns"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/discover-patterns.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 | $0.00035 | $0.01304 |
| Opus 5.5 | $0.00014 | $0.00522 |
| Sonnet 5.5 | $0.00007 | $0.00261 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
discover-patterns 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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discover Patterns
Analyze a codebase to discover and document its implicit architectural and implementation patterns.
Workflow
1. Scope and explore
- Confirm scope with the user: full codebase (default), specific packages/directories, or specific concern.
- Explore the scoped code using parallel explore subagents. Read source files, test files, config files, and build files.
- Classify files by type:
has_go,has_proto,has_ts,has_infra, etc.
2. Identify candidate patterns (Opus)
Launch up to 4 concurrent subagents (subagent_type="generalPurpose", model: opus per subagent-model-routing — architecture-level pattern recognition requires deep reasoning across the codebase), each covering a group of pattern categories from the taxonomy. Each subagent reads all relevant files and identifies candidate patterns with a signature the counting stage can apply mechanically.
| Subagent | Categories | Requires |
|---|---|---|
| Structure & Layering | STRUCT | Any source files |
| Error Handling & Observability | ERR, OBS | Any source files |
| Config & DI | CFG, DI | Any source files |
| Testing | TEST | Any source + test files |
| Transport | XPORT | HTTP/gRPC code present |
Each subagent receives:
- The scoped file list for its relevant file types
- Reference: reference-pattern-taxonomy.md for what to look for
For each candidate pattern, record:
- Name: short descriptive name
- Description: what the pattern is and how it works
- Search signature: a concrete way to find further occurrences. A grep regex, file glob, AST predicate (e.g. "calls to
context.Background()outsidemain.go"), or symbol pattern. Must be specific enough that the counting stage applies it mechanically. - Seed exemplars: 1-2 file:line references the discovery subagent already saw
This stage does NOT compute confidence or gather exhaustive exemplars. Step 2.5 handles that.
2.5. Count occurrences per pattern (Haiku fan-out)
What ships with it
1 file 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.
- 1mo ago First seen · 132 lines · 35 tokens per session scan A 0d9fdae96fc4
discover-patterns is a skill published in the GitHub repository paultyng/skill-issue (8 stars, last pushed 11d ago), licensed MIT. It adds 35 tokens to every session and 1,304 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
pr-alignment-loop
Iterate a PR to its final form by running two opposing reviewer droids (reviewer-robustness and reviewer-minimalist) in a bounded back-and-forth loop. The main orchestrator synthesizes their feedback, makes edits, runs tests, and stops when both approve, on stagnation, or after 3 rounds. Use when the user asks to…
deep-review
Evidence-based deep code review rubric — severity + confidence findings across maintainability, correctness, security, performance, and testing. Push for ambitious structural simplification (code judo), not just local cleanup. Escalate hands-on triage to the code-reviewer agent.
gh-address-comments
Triage and address open GitHub PR review and conversation comments using the gh CLI. Use when the user wants to "address PR comments", "resolve review threads", or "respond to reviewers" on the current branch's pull request.
blind-spot-pass
Run a pre-build blind spot pass before the agent builds anything. Treat the user's prompt as the map and the real project as the territory: classify gaps across known knowns, known unknowns, unknown knowns, and unknown unknowns (with deps, edge cases, and blast radius under unknown unknowns); ask 5 to 10 high-leverage…
merge-open-prs
Review, verify (Docker by default), and auto-merge open PRs when CI, reviews, and local verification pass. Batch up to 10 PRs per run. Use when the user wants to merge all open PRs, clear the PR queue, or run /merge-open-prs.
deslop
Remove AI-generated code slop and clean up code style.