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 synaptiai/synapti-marketplace --skill preflight-checksgit clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote 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/synaptiai/synapti-marketplace/preflight-checks)<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/preflight-checks"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/preflight-checks/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/synaptiai/synapti-marketplace/preflight-checks"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/preflight-checks.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 | $0.00064 | $0.00942 |
| Opus 5 | $0.00032 | $0.00471 |
| Sonnet 5 | $0.00013 | $0.00188 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
preflight-checks 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 2d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-flight Checks
Contract
Iron law: no LLM calls in pre-flight — every check is a bash command with a pass/fail exit code, and a failed pre-flight stops the workflow before any token is spent on planning. Consumed by /flow:start Phase 0 (PRE-FLIGHT); the runnable bash lives in plugins/flow/commands/start.md and is never invoked as Skill(preflight-checks). That bash returns a ### Pre-Flight section with ISSUE_NUM=, PREFLIGHT_ERRORS=, PREFLIGHT_WARNINGS=, PREFLIGHT_STATE=PASSED|BLOCKED, then one PREFLIGHT_FAIL=<reason> line per error and one PREFLIGHT_WARN=<reason> per warning. PREFLIGHT_STATE=BLOCKED halts before EXPLORE. Permitted skips: none — warnings surface and proceed; errors always halt.
What Pre-flight Protects
Pre-flight is the cheapest filter: it runs before EXPLORE, before any agent dispatch, before any reasoning, and fails fast on conditions that would invalidate everything downstream. Because it is honest about what it proves, downstream phases trust their preconditions and stop re-checking them.
The Checks
| # | Check | Failure mode it prevents |
|---|---|---|
| 0 | Issue number present and all-digit | Non-numeric argument reaching the prompt context or a shell (git checkout -b "feature/issue-${ISSUE_NUM}-..."). |
| 1 | Clean git state (git status --porcelain empty) |
Starting a feature branch on unrelated dirty state and shipping it in the PR. |
| 2 | Not on detached HEAD (git symbolic-ref HEAD) |
Commits with no branch reference that vanish on the next checkout. |
| 3 | gh auth status succeeds |
Spending tokens on planning, then failing at the first gh issue view. |
| 4 | Issue exists and state is OPEN |
Working a closed, deleted, or mistyped issue — a PR with nothing to close. |
| 5 | git ls-remote --exit-code origin succeeds |
Reaching the push step and discovering the remote is unreachable or misconfigured. |
| 6 | Current branch already matches issue-$ISSUE_NUM (warning only) |
Re-starting an issue already in progress on this branch — recoverable, so warn not fail. |
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.
- 2d ago Changed · -4 lines 7d52ba60f0a0
- 9d ago First seen · 59 lines · 64 tokens per session scan A 177f6201d9a8
preflight-checks is a skill published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 942 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
create-pr
Creates a GitHub Pull Request on the current branch with a description focused on WHAT changed (not HOW). Uses emojis in the title and description. Use when the user asks to create a PR, open a pull request, or submit changes for review. Triggers on mentions of PR, pull request, merge request, or code review.
document
Run /document pr | changelog | release-note | postmortem (or let it ask) to write the human facing prose about a change. Drafts from the real commits and diff, writing to the right place. Does not write code, tests, or specs.
create-pr
Opens a GitHub PR for the current branch linked to the Pocket issue (Pocket Enterprise). User-triggered recorder — commits traveling state, formats a structured PR body, discovers or creates the PR, and records it in .pocket-meta.json. Trigger on "create-pr", "open a PR", "create pull request", or when…
create-or-update-concepts
Scan and analyze the project codebase to create or update concept files in agents-context/concepts/ (organized by domains/, source/, shared/) and update the README index and Load-When Cheatsheet.
step2-scope-tasks
Break a specification into ordered task groups with explicit context-awareness directives.
step1-write-spec
Gather requirements through structured Q&A, then formalize into a specification document.