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 lalitnayyar/finally --skill gsd-verify-workgit clone --depth 1 https://github.com/lalitnayyar/finallyWrote 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/lalitnayyar/finally/gsd-verify-work)<a href="https://agentmods.dev/skills/lalitnayyar/finally/gsd-verify-work"><img src="https://agentmods.dev/badge/skills/lalitnayyar/finally/gsd-verify-work/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/lalitnayyar/finally/gsd-verify-work"><img src="https://agentmods.dev/badge/skills/lalitnayyar/finally/gsd-verify-work.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 | $0.00013 | $0.00767 |
| Opus 5.5 | $0.00005 | $0.00307 |
| Sonnet 5.5 | $0.00003 | $0.00153 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
gsd-verify-work 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 13d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<codex_skill_adapter>
A. Skill Invocation
- This skill is invoked by mentioning
$gsd-verify-work. - Treat all user text after
$gsd-verify-workas{{GSD_ARGS}}. - If no arguments are present, treat
{{GSD_ARGS}}as empty.
B. AskUserQuestion → request_user_input Mapping
GSD workflows use AskUserQuestion (Claude Code syntax). Translate to Codex request_user_input:
Parameter mapping:
header→headerquestion→question- Options formatted as
"Label" — description→{label: "Label", description: "description"} - Generate
idfrom header: lowercase, replace spaces with underscores
Batched calls:
AskUserQuestion([q1, q2])→ singlerequest_user_inputwith multiple entries inquestions[]
Multi-select workaround:
- Codex has no
multiSelect. Use sequential single-selects, or present a numbered freeform list asking the user to enter comma-separated numbers.
Execute mode fallback:
- When
request_user_inputis rejected (Execute mode), present a plain-text numbered list and pick a reasonable default.
C. Task() → spawn_agent Mapping
GSD workflows use Task(...) (Claude Code syntax). Translate to Codex collaboration tools:
Direct mapping:
Task(subagent_type="X", prompt="Y")→spawn_agent(agent_type="X", message="Y")Task(model="...")→ omit (Codex uses per-role config, not inline model selection)fork_context: falseby default — GSD agents load their own context via<files_to_read>blocks
Parallel fan-out:
- Spawn multiple agents → collect agent IDs →
wait(ids)for all to complete
Result parsing:
- Look for structured markers in agent output:
CHECKPOINT,PLAN COMPLETE,SUMMARY, etc. close_agent(id)after collecting results from each agent </codex_skill_adapter>
Purpose: Confirm what the agent built actually works from user's perspective. One test at a time, plain text responses, no interrogation. When issues are found, automatically diagnose, plan fixes, and prepare for execution.
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.
- 13d ago First seen · 73 lines · 13 tokens per session scan A ab1e7b23e43e
gsd-verify-work is a skill published in the GitHub repository lalitnayyar/finally (0 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 767 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 2026-10-03.
Other skills, from other repositories
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.
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
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.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.