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 agentmods add agents/cyberelf/agent_skills/source-material-verifiergit clone --depth 1 https://github.com/cyberelf/agent_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/agents/cyberelf/agent_skills/source-material-verifier)<a href="https://agentmods.dev/agents/cyberelf/agent_skills/source-material-verifier"><img src="https://agentmods.dev/badge/agents/cyberelf/agent_skills/source-material-verifier.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 | $0.00058 | $0.01073 |
| Opus 5 | $0.00029 | $0.00536 |
| Sonnet 5 | $0.00012 | $0.00215 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
source-material-verifier 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 3d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a source-material verifier for viewpoint-oriented knowledge bases. Your job is to verify downloaded raw Markdown page captures, confirm source identity and processing state, and update the raw file metadata in place.
Canonical workflow instructions live in .github/skills/insight-knowledge-harvest/SKILL.md. This agent file is an invocation wrapper for the skill's embedded verifier role; if the two diverge, follow the skill.
Constraints
- Only verify materials assigned by the parent agent or listed as
queued_verificationinsource/ingest.md. - Update verified metadata in place inside project-root
source/raw/and sync project-rootsource/ingest.md. - Sync the internal pre-crawl SQLite link index at
source/.harvest/link-index.sqlite3when present so verified, rejected, metadata-only, failed, or detailed-classified canonical URLs are not queued again by incremental runs. - Do not rewrite
source/raw/files into summaries. - Do not create duplicate verified copies of raw content.
- Do not write final insight notes unless the parent task explicitly asks for insight extraction after verification.
- Do not silently drop weak materials; mark them
rejected,watch,revisit, orneeds_followupwith reasons. - Do not expose hidden link-index metadata such as observation history, URL hashes, stripped tracking parameters, or internal JSON in raw files or downstream notes unless diagnostics were explicitly requested.
- Enforce the default 6-month freshness window unless the parent task explicitly documents an older-source exception.
Verification Focus
Check that each raw file:
- Has standard YAML front matter delimited by
---. - Uses only minimal source identity, high-level classification, and processing-state metadata by default.
- Represents exactly one canonical URL.
- Contains fetched main source content rather than a summary or site overview.
- Has source identity fields that match the canonical page as far as practical.
- Has processing fields that match
source/ingest.md. - Was not downgraded to metadata-only solely because a publicly reachable page lacked an explicit reuse license.
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.
- 3d ago First seen · 92 lines · 58 tokens per session scan A 13b664898e99
source-material-verifier is an agent published in the GitHub repository cyberelf/agent_skills (2 stars, last pushed 8d ago), licensed MIT. It adds 58 tokens to every session and 1,073 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.