A pre-release self-check for judging how complete, correct, polished, and tested the current work really is.

Use it to review files, changes, and produced results before release, then record what is good, what is missing, and what still needs checking.

It helps expose unfinished requirements, known bugs, weak spots, and unverified assumptions before work is shipped.

preflight — Skill for Claude Code by pandysp/claude-plugins

Install

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.

Any agent

npx skills add pandysp/claude-plugins --skill preflight

Clone the repo

git clone --depth 1 https://github.com/pandysp/claude-plugins

Made for: Claude Code.

Or install preflight, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pandysp/claude-plugins/preflight/github.svg)](https://agentmods.dev/skills/pandysp/claude-plugins/preflight)

Your own site

<a href="https://agentmods.dev/skills/pandysp/claude-plugins/preflight"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pandysp/claude-plugins/preflight"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/preflight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,203 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00098	$0.01203
Opus 5.5	$0.00039	$0.00481
Sonnet 5.5	$0.00020	$0.00241
Haiku 4.5	$0.00010	$0.00120

Measured 1mo ago against content hash 2ea03e26bc13, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

plugins/preflight/skills/preflight/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preflight: honest assessment before shipping

Stop and honestly assess: how happy are you with the current state of the work?

Not "are you happy" (binary, invites a polite yes). "HOW happy" (graduated, demands nuance). This is your chance to surface everything you've been holding back, rationalizing, or planning to mention later.

Modes

Usage: preflight [--fix] (use the host's skill invocation syntax).

Without --fix: assess and report. Wait for the user to choose what to act on.
With --fix: assess, fix, verify, and repeat. The flag authorizes fixes within the current task, not new scope, destructive actions, or bypassing permissions.

How to reflect

Review what actually exists. Read files, check the diff, examine the produced artifacts. Don't assess from memory.

Self-assessment has a built-in blind spot: you're grading your own work. For high-stakes ships, follow second-opinion if available and fold any findings into the assessment.

Then assess across these dimensions:

Completeness

Is everything implemented or written? Were any requirements quietly dropped, or items deferred without discussion?

Correctness

Does it actually do what it claims? Any known bugs, edge cases, or unverified assumptions?

Quality

Is this clean, correct, and elegant, or were corners cut? Would you be proud to show this to a sharp peer who'd notice problems?

Verification

Has it been properly checked (tests, manual usage, rendered output, peer-read, whatever's appropriate)? Anything that should have been verified but wasn't?

Loose ends

What's unfinished or deferred? Any risks or fragilities introduced?

NOW vs LATER

Default concrete issues in the current work to NOW. Bugs, missing requirements, verification gaps, stale docs, and quality problems a sharp reviewer would flag belong here. Being preexisting, small, tedious, or more work than expected is not a reason to defer them.

LATER is the exception: an independent enhancement not needed to ship the current work correctly, or something the user explicitly chose to defer. Explain why leaving each item does not compromise this ship; for user-directed deferrals, record the decision and any remaining risk. Don't turn unfinished work into a follow-up just to finish the session.

Read the full file on GitHub · 75 lines

Changes

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 · +25 lines · +6 tokens per session 2ea03e26bc13
1mo ago First seen · 50 lines · 92 tokens per session scan A e7d1a5982f19

Subscribe to this mod's changes

preflight is a skill published in the GitHub repository pandysp/claude-plugins (6 stars, last pushed 7d ago), licensed MIT. It adds 98 tokens to every session and 1,203 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 2026-08-31.

Testing

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.

davila7/claude-code-templates · 43 tokens

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".

apache/tika · 50 tokens

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.

davidondrej/skills · 68 tokens

preflight