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 randommonicle/claude-skills --skill deliverable-integritygit clone --depth 1 https://github.com/randommonicle/claude-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/randommonicle/claude-skills/deliverable-integrity)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/deliverable-integrity"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/deliverable-integrity/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/randommonicle/claude-skills/deliverable-integrity"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/deliverable-integrity.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 | $0.00116 | $0.00634 |
| Opus 5 | $0.00058 | $0.00317 |
| Sonnet 5 | $0.00023 | $0.00127 |
| Haiku 4.5 | $0.00012 | $0.00063 |
Grade A, and why
deliverable-integrity 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 11d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deliverable integrity
Three gates distilled from this library's own field notes (LESSONS_LEARNED lessons 1, 2, 5), all found on one real job: a CV whose star glyph rendered perfectly and parsed as garbage, a rewrite that quietly promoted "supported investigations" into "conducted investigations" and invented a job title, and date facts only the document's owner could resolve.
Gate 1 — claims: diff the rewrite claim by claim
The dangerous failure of an AI rewrite is not that it sounds like AI; it is that the claims move. Diff against the source claim by claim, not sentence by sentence. Where the rewrite says more than the original, the original wins unless the owner confirms the stronger claim in writing. Keep a record of reverted inflations so they cannot creep back in a later edit.
Gate 2 — gaps: loud placeholders, never plausible guesses
Facts the generator does not hold render as unmissable tokens — [[TOKEN: question for the owner]] — collected once into questions the owner can actually answer. Gate the build on an
allowlisted token set so an unresolved gap is a build failure, not a shipped guess. A
contradiction in owner-supplied facts holds the slot open; never resolve it by picking the
convenient side.
Gate 3 — parsing: re-extract and assert
Rendering and parsing are different code paths, and a machine reader uses the one you did not look at. Any document destined for machine consumption gets verified by re-extracting its text and asserting: required strings present, banned strings absent, no glyphs outside the expected range — fail the build otherwise. The manual version: select all, copy, paste into Notepad. What Notepad shows is what the parser sees.
What this skill does not do
It does not verify code or history citations (verified-citations), police prose style (unslop-text), or substantiate marketing claims (substantiate-outward-claims). It keeps a generated document's factual content honest and its text layer machine-readable.
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.
- 11d ago First seen · 47 lines · 0 tokens per session scan A 502e8b21a045
deliverable-integrity is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 4d ago), licensed Apache-2.0. It adds 116 tokens to every session and 634 once invoked, about $0.0006 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.