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 jstoup111/ai-conductor --skill finishgit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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/jstoup111/ai-conductor/finish)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/finish"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/finish/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/jstoup111/ai-conductor/finish"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/finish.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 | $0.00048 | $0.01718 |
| Opus 5 | $0.00024 | $0.00859 |
| Sonnet 5 | $0.00010 | $0.00344 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
finish 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 3d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
FINISH keeps human authority over interactive publication choices, authors the retained pull request's reader-facing title and body when the coordinator observes them as still unauthored, and retains one reader-facing quality judgment for that title and body. The engine-owned publication coordinator observes evidence, selects which of those two passes is required, advances deterministic publication transitions, and records completion.
Responsibility Boundary
The coordinator, not this skill, owns every mechanical action: verifying SHIP and publication evidence, creating or reusing a PR identity, pushing commits, creating durable shipment evidence, marking a PR ready, and recording the final outcome.
For author_pr_prose and judge_pr_prose alike, this skill may
inspect and repair only the retained PR's title and body.
It must not create, push, merge, ready, or otherwise change a PR; write shipment
evidence, completion markers, or outcome records; or infer deterministic
repository or external state.
Reading the feature's own diff, specification, plan, and story artifacts to write that title and body is inside this boundary, not outside it — authoring reader-facing prose is exactly the work FINISH keeps for a provider. Only publication mechanics are the coordinator's.
Fresh Verification
1. Fresh Verification
The FINISH provider session never runs tests or launches full-suite or aggregate verification.
It consumes the coordinator's evidence; missing or stale suite proof belongs to test_suite.
Before any provider receives FINISH work, the coordinator uses the engine's configured aggregate verifier for current completion evidence. It reuses a current passing result; when evidence is missing or stale, the verifier obtains the required current result. A previous session's report, marker, or provider response does not substitute for current repository and external evidence.
Both passing verdicts are equally acceptable proof: REUSED for a current
passing result the verifier reused, and EXECUTED for one it obtained during
this pass. The coordinator never requires EXECUTED when REUSED is available
— re-running a suite that is already current buys no evidence and costs the
whole suite's runtime.
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.
- 3d ago Changed · +3 lines f090485fa51d
- 9d ago First seen · 164 lines · 48 tokens per session scan A 20d7b405f12e
finish is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 1,718 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 2026-08-31.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.