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 jukanntenn/glm-plan-usage --skill preflightgit clone --depth 1 https://github.com/jukanntenn/glm-plan-usageWrote 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/jukanntenn/glm-plan-usage/preflight)<a href="https://agentmods.dev/skills/jukanntenn/glm-plan-usage/preflight"><img src="https://agentmods.dev/badge/skills/jukanntenn/glm-plan-usage/preflight/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/jukanntenn/glm-plan-usage/preflight"><img src="https://agentmods.dev/badge/skills/jukanntenn/glm-plan-usage/preflight.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 | $0.00104 | $0.00473 |
| Opus 5.5 | $0.00042 | $0.00189 |
| Sonnet 5.5 | $0.00021 | $0.00095 |
| Haiku 4.5 | $0.00010 | $0.00047 |
Grade A, and why
preflight 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 2mo 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.
What it actually says
Generate an end-to-end acceptance manual by diffing the current working tree against the last released version.
Process
- Identify versions — find the latest tag (
git describe --tags --abbrev=0) and confirm the target scope (default: diff from that tag to HEAD). - Gather the full diff —
git diff <tag>..HEADplusgit log --oneline <tag>..HEAD. Read changed source files to understand intent behind each change — not just what lines moved, but what behavior changed for the user. - Classify every change — for each diff, determine: new features, modified behavior, fixed bugs, removed functionality, config changes, and breaking changes.
- Produce the acceptance manual — output a structured checklist organized by functional area (not by file or commit) to a file using output format bellow. For each item include:
- What changed (one-line summary)
- How to verify it (concrete steps: which command to run, what output to expect, which config field to check)
- Edge cases or risks to watch for
Output format
# Preflight Acceptance Manual — <tag> → HEAD
## Summary
<one-paragraph overview of all changes>
## 1. <Functional Area>
- [ ] **<change summary>** — <verification steps>
- [ ] **<change summary>** — <verification steps>
## 2. <Functional Area>
...
Keep the manual concise, actionable, and free of implementation details. Every checklist item must be verifiable by running a command or observing a behavior — no vague items like "verify it works."
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.
- 2mo ago First seen · 45 lines · 104 tokens per session scan A 45dc8c4811ef
preflight is a skill published in the GitHub repository jukanntenn/glm-plan-usage (14 stars, last pushed 4mo ago), licensed MIT. It adds 104 tokens to every session and 473 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
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.…
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…
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.
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.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.