[rig-tasks] Add 10 rig samples — 2026-10-08

[github-actions]

Summary

Added 10 new rig sample files to skills/rig/samples/ (numbered 521–530; the repository's highest existing sample number was 520, not 67 as a naive glance at low-numbered files suggested — samples 68-520 already existed).

The rig-expander and task-generator subagents were unavailable this run (every invocation failed with 400 Cannot translate Copilot request feature 'frequency_penalty' between Responses and Chat Completions., an infrastructure/model-routing issue unrelated to the task content). I generated the 4 new task descriptions directly and hand-wrote all 10 rig programs following skills/rig/SKILL.md, agent-api.md, composition.md, prompt-intents.md, and dynamic-workflows.md, then typechecked and linted each one.

#	File	Description	Typecheck
1	521-commit-type-tagger.md	Classify recent commits into conventional-commit types via s.enum/s.record	pass
2	522-tsconfig-nested-validator.md	Validate tsconfig.json against a nested s.object/s.record schema via p.read	pass
3	523-repair-addon-demo.md	repair() addon with higher maxTurns for structured-extraction retries	pass
4	524-healthcheck-timeout.md	p.bash health probe with timeout() addon	pass
5	525-lint-test-gate-workflow.md	workflow() chaining lint → test → gate agents sequentially	pass
6	526-glob-tagger-aggregator.md	p.glob fan-out to a tagger subagent, aggregated into s.record(s.array(...))	pass
7	527-review-readiness-report.md	p.bash + p.read/p.readOptional combined into a mixed-field s.object report	pass
8	528-basename-similarity-finder.md	Custom defineTool (no bash/read) for basename similarity scoring	pass
9	529-parallel-wordfreq-aggregator.md	workflow() fan-out/fan-in via Promise.all across two subagents, merged by an aggregator agent	pass
10	530-bug-template-stub-writer.md	Conditional p.write side effect gated on a p.bash existence check, with s.enum inside s.array	pass

Typecheck failures

No failures this run — all 10 sample programs typechecked and linted cleanly after two small fixes applied during development (see the companion analysis issue for details: call() requires a string prompt rather than undefined for no-input agents, and parallel() return typing needed to match Promise.all usage exactly as the existing 412-parallel-branch-analysis-workflow.md sample does).

Tasks run

• (reused) Run p.bash to fetch recent commits, classify each commit message into an s.enum of conventional-commit types, and return an s.record keyed by type mapping to matching commit subjects.
• (reused) Use p.read to load tsconfig.json and validate it against a deeply nested s.object schema (compilerOptions with optional strict/target/paths as s.record(s.string, s.array(s.string))), outputting a validation report.
• (reused) Build an agent with a strict s.object output schema and attach the repair() addon with a higher maxTurns to demonstrate automatic re-prompting on malformed output.
• (reused) Run a p.bash health-check command with an explicit timeout() addon, returning s.object with status: s.enum('ok','timeout','error') and durationMs: s.number.
• (reused) Compose a workflow (not a single agent) chaining three agents sequentially: lint-check, test-check, and a gate agent combining both into an approved/blocked decision.
• (reused) Use p.glob to find source files, fan out to a tagger subagent that assigns topical tags from an s.enum set, then aggregate into an s.record(s.string, s.array(s.string)) of tag to file paths.
• (new) Build an agent that uses p.bash to run git diff --stat and p.read to load CONTRIBUTING.md, combining both signals into a review-readiness report.
• (new) Define a custom tool computing basename similarity, combined with p.glob to find near-duplicate basenames.
• (new) Compose a workflow with two subagents run in parallel, each computing word frequency over different directories, merged by an aggregator agent.
• (new) Use p.read + conditional p.bash existence check + p.write to create a bug-report issue template stub only if missing.

Generated by Daily Rig Task Generator · copilot · auto · 267.1 AIC · ⌖ 12 AIC · ⊞ 9.4K · ◷

[github-actions]

🧠 Matt Pocock Skills Reviewer is reviewing this pull request using Matt Pocock's engineering skills...