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 ogulcancelik/agent-skills --skill preflightgit clone --depth 1 https://github.com/ogulcancelik/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/ogulcancelik/agent-skills/preflight)<a href="https://agentmods.dev/skills/ogulcancelik/agent-skills/preflight"><img src="https://agentmods.dev/badge/skills/ogulcancelik/agent-skills/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/ogulcancelik/agent-skills/preflight"><img src="https://agentmods.dev/badge/skills/ogulcancelik/agent-skills/preflight.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 | $0.00049 | $0.01529 |
| Opus 5.5 | $0.00020 | $0.00612 |
| Sonnet 5.5 | $0.00010 | $0.00306 |
| Haiku 4.5 | $0.00005 | $0.00153 |
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 1mo 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preflight
Preflight reduces implementation bias. The implementing agent becomes attached to its diagnosis and design. A fresh specialist that sees the problem and code, but not the proposed solution, can find regressions before the design is locked.
The flow is:
investigate → risk challenge → concise contract → approve → implement → verify → simplify → finish
Rules
Use this skill only when the top-level user explicitly requests preflight or a risk gate. Never invoke it from a delegated child. If preflight was not requested, suggest it once and wait.
The main agent owns investigation, scope, implementation, and communication. Children only challenge, verify, review, or simplify. Give each child one job. Reuse it only to recheck its own findings.
Prefix every child assignment with:
You are a bounded preflight child. Do not invoke preflight, delegate work, or spawn agents. Complete only the assigned analysis and return it to the parent.
Always run the pre-implementation risk challenge. For meaningful code changes, also run a contract verifier and regression reviewer after implementation. Run a simplifier when the patch adds meaningful structure. Add an evidence challenger only when the reproduction is uncertain or the change is unusually risky. Do not create agents merely to fill a process.
1. Investigate
Read repository instructions and trace the real execution path before planning. For bugs, prefer a real user-path reproduction, then an existing integration signal, then an owning-layer test. If none is available, label the diagnosis as a hypothesis. For features, define one observable acceptance signal.
Separate facts from assumptions. Investigation cannot expand the request.
2. Run the independent risk challenge
Give a fresh agent the raw request, evidence, repository instructions, relevant code, and existing tests. Do not give it the main agent's diagnosis, implementation plan, architecture, or proposed patch.
Use this prompt:
Find concrete regressions this requested change could cause. For each finding, cite the existing behavior, exact code path, evidence, and causal failure chain. Do not suggest implementation designs, tests, mitigations, general improvements, defensive hardening, or hypothetical risks without evidence. Report unknowns separately.
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.
- 1mo ago Changed · +14 lines 2bf79a8885d5
- 1mo ago First seen · 165 lines · 49 tokens per session scan A 865e671b13d6
preflight is a skill published in the GitHub repository ogulcancelik/agent-skills (80 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 1,529 once invoked, about $0.0002 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
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…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…