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 lenar-amirov/product-pipeline-public --skill ingestgit clone --depth 1 https://github.com/lenar-amirov/product-pipeline-publicWrote 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/lenar-amirov/product-pipeline-public/ingest)<a href="https://agentmods.dev/skills/lenar-amirov/product-pipeline-public/ingest"><img src="https://agentmods.dev/badge/skills/lenar-amirov/product-pipeline-public/ingest/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/lenar-amirov/product-pipeline-public/ingest"><img src="https://agentmods.dev/badge/skills/lenar-amirov/product-pipeline-public/ingest.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 | $0.00101 | $0.00913 |
| Opus 5 | $0.00051 | $0.00456 |
| Sonnet 5 | $0.00020 | $0.00183 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
ingest 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingest — /ingest <file | Confluence pageID | pasted data>
In real corporate work the most valuable data arrives through the side door — someone else's deck, an ad-hoc export, a wiki page. This job turns such an artifact into typed evidence in the registry instead of a manual retyping exercise.
1. Acquire
- PDF (deck, report): render pages to images —
python3 tools/scripts/render-pdf.py <file.pdf> <scratch_dir> [first] [last]— then Read the images (batch 5-10 pages per pass). - PPTX: convert to PDF first if possible (
soffice --convert-to pdf), or ask the PM for a PDF export. - xlsx/csv: read directly (xlsx skill if available).
- Confluence page: fetch via MCP (
confluence_get_pagewith pageID). - Pasted text/numbers: work with it as-is.
2. Extract
Pull out every number and finding relevant to the initiative's tracks: metric, value, definition (exactly as the source states it), and location ("слайд 17", "стр. 3, таблица 2"). Note the data window (dates) — it goes into the source record.
3. Map onto hypotheses (the core of the job)
Load open hypotheses: python3 tools/scripts/hypotheses.py show <dir>.
For each extracted finding, classify:
- Supports Hx → propose upgrade:
hypotheses.py set Hx --status confirmed --type REAL --confidence 0.N --add-source "<file>::слайд NN — <what it says>" - Contradicts Hx → propose refutation (
--status refuted) and say explicitly that REAL beats the previous INFERRED/SYNTHETIC — document the delta in the narrative file. - Contradicts ANOTHER source already in the registry → do NOT silently
average:
hypotheses.py set Hx --flag data_inconsistency --note "source A vs source B: X vs Y"and add the reconciliation question to the open questions for the analyst. - Relevant but matches no hypothesis → candidate NEW hypothesis
(
hypotheses.py add) — ask the PM before adding. - Not mapped → append to
research/inbox-notes.mdwith source refs, so nothing is lost.
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 · 74 lines · 101 tokens per session scan A f1c842d7b12d
ingest is a skill published in the GitHub repository lenar-amirov/product-pipeline-public (12 stars, last pushed 23d ago), licensed MIT. It adds 101 tokens to every session and 913 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 2026-08-30.
Other skills, from other repositories
preserve-security-evidence
Preserve security evidence before analysis, containment, or remediation changes it. Use for artifacts, volatile host state, vulnerability validation, records, logs, screenshots, commands, hashes, timelines, and reproducible handoffs.
ingest
Process raw files from vault/sources/ into linked wiki pages. Actions - all (every unprocessed source), file (one specific source), overview.
deliverable-creation
Produce polished, consulting-quality deliverables including slide decks, reports, memos, and one-pagers. Use this skill when the user mentions: create a deck, build a presentation, make slides, write a report, executive summary, one-pager, synthesis, storyboard, slide structure, pyramid principle, consulting deck…
html-report
Parse data files of many formats — CSV/TSV, Excel (.xlsx), SQLite, JSONL/NDJSON, JSON, Markdown, plain text, and log files — and generate a stunning, self-contained, single-file HTML experience that visualizes the data: a Three.js animated hero, GSAP scroll animations, Tailwind styling, column-profiled data tables…
ddt-baseline-sync
A skill that imports staffing, work-hour, or project-plan spreadsheets and CSV files into a historical project baseline. A baseline is past project data used to improve future work-hour estimates.
csv-exporter
Generate properly formatted Teamwork CSV files from Functional Requirements Documents. Converts FRD requirements into CSV backlog with task hierarchy, priorities, story points, and estimated hours. Automatically populates estimated time from story point conversion. Invoke when user asks to "export to CSV", "create…