A work-checking procedure that runs the validation tests or checks linked from an issue and reports each result.

Use it before closing an issue or pull request, or when someone asks whether an issue is complete. It maps validation IDs to commands or CI steps and runs them.

It helps confirm that an issue is really finished instead of trusting its claim alone. It also shows which specific checks passed or failed.

verify-task — Skill by tikoci

Install

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.

agentmods

npx agentmods add skills/tikoci/rosetta/verify-task

Any agent

npx skills add tikoci/rosetta --skill verify-task

Clone the repo

git clone --depth 1 https://github.com/tikoci/rosetta

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,423 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00047	$0.01423
Opus 5	$0.00023	$0.00711
Sonnet 5	$0.00009	$0.00285
Haiku 4.5	$0.00005	$0.00142

Measured 2d ago against content hash 59f2a672c569, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-task 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 2d 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.

.github/skills/verify-task/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Task

Closes the loop between a work item's claimed acceptance and what's actually proven. Reads the V-* rows cited in the issue's ## Validation section (per the work-item template), looks each up in VALIDATION.md, runs the proof, reports green/red.

When to use

A PR is about to claim Closes #N and you want to confirm the cited validation rows are actually green.
A user asks "is this issue really finished?"

When NOT to use

For an issue that cites no V-* rows (pure-doc work). There's nothing to run.
As a substitute for code review.

Procedure

Resolve the work item. An issue number → gh issue view <n> and pull the V-* IDs from its ## Validation section — falling back to scanning acceptance bullets for older issues that predate the template (also check any archived tasks/done/T-*.md file the issue names as its full spec). T-0037 → read tasks/T-0037-npm-prerelease-dist-tag-channel.md frontmatter directly (the one still-in-flight file-based task).
Look up each V-* in VALIDATION.md. Pull the Proven by, Status, and Tracked by columns. This tells you whether the invariant is already enforced, non-blocking, CI-only, or still a declared gap.

Run the proof.

Run make verify — it covers V-typecheck, V-lint, V-unit, V-tool-registry, and V-retrieval-floor in one command (requires a populated DB). It runs bun test src/mcp-contract.test.ts without ROSETTA_REAL_DB_TESTS=1, so the real-DB blocks behind V-tool-shapes and V-tool-budget are skipped — run those separately with ROSETTA_REAL_DB_TESTS=1 bun test src/mcp-contract.test.ts against a populated DB. For CI-only invariants (V-db-min-content, V-bunx-*) there is no local equivalent; those are only proven by a release run.

For more targeted checks, map common V-* IDs to commands:

V-* ID	Command
V-typecheck	`bun run typecheck`
V-lint	`bun run lint`
V-unit	`bun test`
V-tool-registry	`bun test src/mcp-contract.test.ts` (Block A, always runs)
V-tool-shapes	`ROSETTA_REAL_DB_TESTS=1 bun test src/mcp-contract.test.ts` (Block C, needs populated DB)
V-tool-budget	`ROSETTA_REAL_DB_TESTS=1 bun test src/mcp-contract.test.ts` (Block B, needs populated DB)
V-retrieval-floor	`bun run src/eval/retrieval.ts`
V-retrieval-self	`bun run src/eval/self-supervised.ts`
V-canonicalize	`bun test src/canonicalize.test.ts src/canonicalize.fuzz.test.ts`
V-classifier	`bun test src/classify.test.ts`
V-schema-roundtrip	`bun test src/schema-roundtrip.test.ts`
V-extract-videos	`bun test src/extract-videos.test.ts`
V-http-handshake	`bun test src/mcp-http.test.ts`
V-stdio-handshake	`bun test src/mcp-stdio-client.test.ts`
V-tui-mcp-parity	`bun test src/browse-parity.test.ts`
V-cli-flag-uniformity	`bun test src/cli-help.test.ts`
V-db-wipe-guard	`bun test src/query.test.ts`
V-release-structure	`bun test src/release.test.ts`

Read the full file on GitHub · 98 lines

Changes

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.

2d ago First seen · 98 lines · 47 tokens per session scan A 59f2a672c569

Subscribe to this mod's changes

verify-task is a skill published in the GitHub repository tikoci/rosetta (43 stars, last pushed 16d ago), licensed MIT. It adds 47 tokens to every session and 1,423 once invoked, about $0.0002 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 2026-08-30.

Planning Testing ai bun claude-code copilot mcp mcp-server

advisor

Interactive workflow advisor that helps you choose optimal AI primitives from agentconfig.org based on your specific workflow needs, skill level, and tooling preferences. Use when deciding which primitives to implement or how to structure your AI configuration.

agentconfig/agentconfig.org · 45 tokens

add-primitive

Add or modify AI primitive definitions in the data layer with correct typing and complete metadata. Use when adding new primitives, updating descriptions, or extending primitive categories.

agentconfig/agentconfig.org · 35 tokens

add-provider

Add a new AI provider to agentconfig.org's comparison system. Use when integrating a new coding assistant (e.g., Cursor, Claude Desktop, GitHub Copilot alternative) with proper type system updates, implementation data, UI components, tests, and documentation.

agentconfig/agentconfig.org · 55 tokens

refresh-provider-docs

Retrieve, normalize, compare, and cite authoritative AI provider documentation to verify what agentconfig.org publishes. Use when checking whether provider config locations, hook events, skills, MCP, custom agents, or precedence claims are still accurate, when adding a provider to the compatibility index, or when…

agentconfig/agentconfig.org · 67 tokens

generate-llms

Generate llms.txt and llms-full.txt files for AI agent consumption following the llmstxt.org standard. Use when updating site content that should be reflected in the llms files, or when building/deploying the site.

agentconfig/agentconfig.org · 51 tokens

create-page

Create a new tutorial/content page on agentconfig.org with proper file structure, routing, and registry entry. Use when adding a new top-level page like /skills, /agents, or /mcp.

agentconfig/agentconfig.org · 44 tokens