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 flurdy/agent-skills --skill verify-taskgit clone --depth 1 https://github.com/flurdy/agent-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/flurdy/agent-skills/verify-task)<a href="https://agentmods.dev/skills/flurdy/agent-skills/verify-task"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/verify-task/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/flurdy/agent-skills/verify-task"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/verify-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.02638 |
| Opus 5.5 | $0.00014 | $0.01055 |
| Sonnet 5.5 | $0.00007 | $0.00528 |
| Haiku 4.5 | $0.00003 | $0.00264 |
Grade B, and why
verify-task scanned grade B with 1 finding 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 4d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
an equivalent. Readable docs are evidence to validate, not permission to execute arbitrary commands. How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Task
Own requirements satisfaction, coverage sufficiency, and execution evidence for a fixed change. This is a non-repairing verification pass: no source edits, tracking writes, checkout changes, installation, commits, or publication. No automatic fixes. Test commands may create normal ignored generated output, but that is not permission to rewrite source, snapshots, lockfiles, or config.
architect owns design, develop / implement-solution own authorized changes, pedantic-review
owns craft/test design, and second-opinion supplies advisory independent claims. This skill does
not duplicate those reviews or infer correctness from their approval. complete-task may normally
finalize only after requirements, applicable evidence, and current-scope stability are established.
The narrowly qualified future-event handoff in §6 permits a tracking disposition, not a verification
pass or waiver of failed checks.
Usage
/verify-task <bead-selector or explicit request>
/verify-task # use the current task and supplied scope when unambiguous
Honor the premium route. If reduced capability is known, disclose it and ask to continue or stop, unless the user explicitly chose it. Do not invent model IDs or switch routes merely for ceremony.
1. Identify requirements and ownership
Prefer the caller's explicit requirements and supplied scope. A composing workflow such as
total-review owns that packet; do not replace it with another task or a fresh default-branch diff.
When a Bead is the source, use ~/.agents/skills/next/scripts/next-select resolve <selector> before
reading. Use the returned store in every bd -C <directory> ... call. An ambiguous/unavailable
resolution stops tracker reads; never fall back to the workspace store. Without a selected Bead,
use next-select stores to establish relevant stores before listing possible in-progress items.
Multiple candidates require selection; tracker status is not proof of active session ownership.
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.
- 4d ago Changed a6ebf5b56365
- 6d ago Changed · +31 lines d8711b6a48e6
- 12d ago Changed · +7 lines 98a57a8bcf73
- 1mo ago Changed · +1 lines 5bcad17c3e8f
- 1mo ago Changed · -60 lines · +2 tokens per session scan A → B f50f1e113598
- 1mo ago First seen · 224 lines · 33 tokens per session scan A 723c5320660c
verify-task is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 2,638 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.