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 olehsvyrydov/AI-development-team --skill verify-landedgit clone --depth 1 https://github.com/olehsvyrydov/AI-development-teamWrote 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/olehsvyrydov/ai-development-team/verify-landed)<a href="https://agentmods.dev/skills/olehsvyrydov/ai-development-team/verify-landed"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/verify-landed/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/olehsvyrydov/ai-development-team/verify-landed"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/verify-landed.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 | $0.00094 | $0.01492 |
| Opus 5.5 | $0.00038 | $0.00597 |
| Sonnet 5.5 | $0.00019 | $0.00298 |
| Haiku 4.5 | $0.00009 | $0.00149 |
Grade A, and why
verify-landed 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 today.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify it landed
A green build is not evidence that your change exists. Removing nothing breaks nothing, so a no-op edit compiles and passes every test. This skill is the short mechanical check that closes that gap.
Observed failure this exists to prevent: a fix for "a batch delete must not abandon itself after destroying part of a folder" never landed, because the string replacement targeted a literal the code expressed as a named constant. It matched nothing. The file compiled, the whole suite passed, and it was reported as fixed. It surfaced a day later only as an unused-field static-analysis smell — the logger added beside the catch block that was never inserted.
The check
1. Grep for the new code, not for a green build. After every behaviour-changing edit, search for the symbol, clause, or string you believe you added, and confirm the match is in the file you intended. One command. Do this even when — especially when — the build is green.
2. Watch the new test fail without the fix. A test written after the fix, that passes immediately, proves nothing about the fix. Either write it first, or stash the change and see it go red. If that is impractical, at minimum assert on the specific new behaviour (the reported failure mode), not on a general happy path that already worked.
3. For a fixed review finding, re-read the file at the reported line. Do not infer "fixed" from a commit message you wrote. The commit message is your intent; the file is the fact. When re-reporting findings as fixed, each one needs a look at the code.
4. Name the enforcement point, not the intention. A criterion like "no bypass", "must be rate limited", "cannot escalate" is met by a mechanism. Identify the class, method, filter, or config directive that refuses the thing. If you cannot name it, the criterion is not met — however complete the feature looks from the happy path.
This is the most common gap in practice: a flag exists, a screen exists, a bootstrap sets it, and nothing reads it. The feature looks finished from every angle except the one it was written for.
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.
- today First seen · 68 lines · 94 tokens per session scan A 490fc1520e51
verify-landed is a skill published in the GitHub repository olehsvyrydov/AI-development-team (17 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 1,492 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 2026-10-19.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
module-regression
Govern cross-module regression in large repositories with a REGRESSION.md ledger that records each module's downstream consumers and executable acceptance command. After a change, run the changed module and every affected downstream command, and use observed exit codes as regression evidence under the project's…
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
test-flakiness
Find flaky tests from CI logs — aggregates pass rates, spots intermittent failures, recommends quarantine. After multiple runs.
moai-workflow-loop
Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.
moai-workflow-testing
Use when writing tests, measuring coverage, or running characterization, performance, or PR-review QA. Comprehensive specialist combining DDD testing, characterization tests, performance profiling, and TRUST 5 quality-assurance validation.