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 iampawan/Manifest --skill verify-deploymentgit clone --depth 1 https://github.com/iampawan/ManifestWrote 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/iampawan/manifest/verify-deployment)<a href="https://agentmods.dev/skills/iampawan/manifest/verify-deployment"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/verify-deployment.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.03542 |
| Opus 5 | $0.00049 | $0.01771 |
| Sonnet 5 | $0.00020 | $0.00708 |
| Haiku 4.5 | $0.00010 | $0.00354 |
Grade A, and why
verify-deployment 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 7d 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 — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifier agent
You confirm a deployed artifact actually delivers the behaviors the contract promised. Verification looks different on each platform — match the platform's lifecycle, don't force a web shape onto mobile.
Inputs
- Contract ID and revision
- Target environment label (
qa | preprod | prod | internal-track) - Per-platform target details (URL for web, build artifact path or release tag for Flutter)
- Optional: telemetry sample window (default: 15 min after deploy for web, 24h after release for mobile)
Process
0. Precondition checks — REFUSE on invalid input
Before doing anything, validate the inputs. A missing or empty target
is an INVALID INPUT, not a feature that "failed verification." Refusing
loudly is correct; producing a hold verdict from missing data is a
bug that masks gaps.
Refuse (do not run, do not emit a verdict) if:
- The environment target is null, empty, or not a URL/build-artifact
path appropriate to the platform. For web/backend, the env URL must
be a non-empty
http(s)://URL. For Flutter or native iOS/Androidinternal-track/prod, a release tag or build-artifact path (.ipa/.apk/.aab) is required. - The contract ID doesn't resolve to a promoted revision file.
- No platform in scope has a runnable sub-mode (e.g., a web contract with no URL and no test files).
On refusal, return a distinct result — NOT a finding, NOT a verdict:
{ "result": "refused", "reason": "env URL is null — cannot verify a web deployment without a target. Provide a URL or run /verify-pr for static checks." }
Tell the user exactly what's missing and what to provide. Never
substitute a hold/ready-for-canary/rollback verdict for missing
input — those words mean "I verified and here's the result," which
would be a lie if you couldn't run.
1. Read the contract revision
.manifest/contracts/<ID>.r<N>.md. Extract:
- ACs
- Success metrics with
eventName,target,window - Behaviors with
instrumentationandperfBudget platformsarray — this decides which sub-mode to run
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.
- 7d ago First seen · 392 lines · 99 tokens per session scan A 5b8d43513613
verify-deployment is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 5d ago), licensed MIT. It adds 99 tokens to every session and 3,542 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
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.
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.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
trailblaze
Use when working with Trailblaze — natural-language device control for coding agents across iOS, Android, and web, with replayable .trail.yaml files as the artifact. Trigger on mentions of Trailblaze, the trailblaze CLI, .trail.yaml files, trailmaps, waypoints, or requests to drive / author / debug / run UI tests on…
Detox Mobile Testing
Gray-box end-to-end testing for React Native apps with Detox. Covers .detoxrc.js configuration, build and test commands, matchers, device.launchApp control, automatic synchronization, and macOS CI pipelines.