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 markoblogo/abvx-agent-skills --skill delivery-preflight-gategit clone --depth 1 https://github.com/markoblogo/abvx-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/markoblogo/abvx-agent-skills/delivery-preflight-gate)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/delivery-preflight-gate"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/delivery-preflight-gate/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/markoblogo/abvx-agent-skills/delivery-preflight-gate"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/delivery-preflight-gate.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 | $0.00088 | $0.00925 |
| Opus 5 | $0.00044 | $0.00463 |
| Sonnet 5 | $0.00018 | $0.00185 |
| Haiku 4.5 | $0.00009 | $0.00093 |
Grade A, and why
delivery-preflight-gate 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 12d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delivery Preflight Gate
Run the smallest useful baseline check before committing the agent to a long implementation loop or before letting a risky branch leave the local workspace.
Use When
- the task is expected to take multiple implementation steps or phases;
- the repo already has build, test, typecheck, lint, or app-run expectations;
- a broken baseline would waste retries or mislead later verification;
- the user is about to ask for an autonomous or low-supervision run;
- a branch should pass a disposable push gate before opening or updating a PR.
For security-sensitive work, run authorized-security-router first when authorization, target boundary, or allowed action level is not already explicit.
If repeated preflight failures reveal a reusable lesson, use agent-learning-layer-triage to decide whether the fix belongs in a memory/context note, durable repo doc, checklist, SKILL.md, script/tool, eval, or golden fixture.
Core Rules
- Deduplicate checks. Do not run the same command under different names.
- Prefer the narrowest commands that still represent the real baseline.
- Verify before planning a large execution loop, not after failure number three.
- Distinguish
baseline already brokenfromtask introduced a regression. - If the baseline is red, stop and present options instead of silently proceeding.
- For push-gate workflows, isolate review and repair work from the main working tree when the tooling supports it.
Workflow
- Identify the mandatory verification surface for this repo.
- Select the minimum command set that represents that surface.
- Run the commands once before starting the long task or before publishing the branch.
- Classify the result:
PREFLIGHT_GREEN: baseline acceptable for execution.PREFLIGHT_RED: baseline broken, flaky, or unverifiable.PUSH_GATE_GREEN: branch is clean enough to push or open/update a PR.PUSH_GATE_RED: branch needs a fix, explicit override, or smaller PR slice before publishing.
- If red, report:
- which commands failed;
- whether the failure appears pre-existing or task-related;
- whether it blocks the planned work or is exactly what phase 1 must fix.
- Require an explicit proceed-or-fix decision before treating the task as safe for autonomous execution or remote publication.
What ships with it
2 files 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.
- 12d ago First seen · 84 lines · 88 tokens per session scan A fb4ef23b08e6
delivery-preflight-gate is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 925 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
bug-fixing
Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
python-testing
Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, Effect v4 CLI tests, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, validating TypeScript package changes, or writing/porting CLI tests against…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
qa
Use to verify that code works correctly — browser-based testing with Playwright, native app testing with computer use, CLI testing, API testing, or root-cause debugging. Supports --quick, --standard, --thorough modes. Triggers on /qa.