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 gulmezeren2-byte/andon --skill verify-with-andongit clone --depth 1 https://github.com/gulmezeren2-byte/andonWrote 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/gulmezeren2-byte/andon/verify-with-andon)<a href="https://agentmods.dev/skills/gulmezeren2-byte/andon/verify-with-andon"><img src="https://agentmods.dev/badge/skills/gulmezeren2-byte/andon/verify-with-andon/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/gulmezeren2-byte/andon/verify-with-andon"><img src="https://agentmods.dev/badge/skills/gulmezeren2-byte/andon/verify-with-andon.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 | $0.00048 | $0.00667 |
| Opus 5 | $0.00024 | $0.00333 |
| Sonnet 5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
verify-with-andon 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 10d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify analysis with andon
You have just produced (or edited) an analysis artifact: a report workbook, a summary table, a set of claimed figures. Before presenting it, verify it with andon. The verification is deterministic arithmetic — your own confidence in the numbers is not a substitute for it.
The discipline
-
Write the spec while the derivation is fresh. For every number you put in the artifact, you know which source rows and filters produced it. Encode exactly that as a check. If you cannot write the check, you do not actually know where the number came from — treat that as a defect in the analysis, not in the spec.
-
Cover four layers, in this order:
schema.*— the assumptions about the source data (unique keys, allowed values, date continuity);reconcile.*— every headline figure against the source, with the same filters you used to derive it;internal.*— totals vs parts, percentages vs 100, derived columns vs their formulas;excel.integrity— if the artifact is a workbook.
-
Run and read:
andon run andon.yaml --jsonExit 0 = all pass. Exit 1 = at least one FAIL: the artifact is wrong or the spec is — find out which before touching anything else. Exit 2 = REVIEW flags: report them to the user verbatim; do not resolve them yourself. Exit 3 = nothing was verified (a check could not run, or every check was skipped): fix the spec or say plainly that the claim is unverified. Exit 4 = broken spec.
-
Report the verdict with the artifact. Include the counts (passed/failed/review) and the honesty block's "Never read" list. A clean verdict is part of the deliverable; a dirty one is the deliverable.
Hard rules
- Never loosen a tolerance, add a
skip:, or narrow awhere:to make a check pass without stating in your response exactly what you changed and why. A silently weakened spec is worse than no spec. - Never present a number the spec does not cover as if it were verified. Say which figures are covered and which are not.
- If a cell read fails with "no cached value" (library-written workbook), point the check at the underlying data range instead of the formula cell.
- Prefer failing loudly over passing quietly: when unsure between two ways to write a check, write the stricter one and let the human relax it.
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.
- 10d ago First seen · 61 lines · 48 tokens per session scan A 1a91f35dff17
verify-with-andon is a skill published in the GitHub repository gulmezeren2-byte/andon (1 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 667 once invoked, about $0.0002 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
excel
A tool for managing Excel configuration sheets used in game development. It can query and edit spreadsheet data using SQL, a language for selecting and changing structured data.
excel
A game-development tool for managing Excel configuration tables through commands. It can query, edit, search, format, and reorganize spreadsheet data, including data across files.
excel
A command-line tool for managing Excel configuration spreadsheets used in game development. It can query spreadsheet data with SQL, including filtering, summaries, and joins between files, then returns JSON results.
excel-hygiene
A rigorous "second pair of eyes" on any xlsx before it goes out. Runs a deterministic script for precise MECHANICAL checks (numbers as text, hardcoded-over-formula, cell errors, truncated SUM, percent as whole number), then reasons across the full spreadsheet-error taxonomy (Panko 2008: violations vs errors…
xlsx-engineer
You are the XLSX Engineering Specialist. You create, edit, analyze, and validate Excel spreadsheet files with professional formatting, working formulas, and zero errors.
xlsx-recover-data
This skill covers recovering missing values (typically marked with "???") in Excel workbooks where multiple sheets contain interrelated financial data. The core challenge is identifying the mathematical relationships between sheets and using known values to back-compute unknowns. This pattern appears frequently in…