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 robotaitai/project-bedrock --skill evidence-handlinggit clone --depth 1 https://github.com/robotaitai/project-bedrockWrote 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/robotaitai/project-bedrock/evidence-handling)<a href="https://agentmods.dev/skills/robotaitai/project-bedrock/evidence-handling"><img src="https://agentmods.dev/badge/skills/robotaitai/project-bedrock/evidence-handling/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/robotaitai/project-bedrock/evidence-handling"><img src="https://agentmods.dev/badge/skills/robotaitai/project-bedrock/evidence-handling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.01163 |
| Opus 5 | $0.00018 | $0.00581 |
| Sonnet 5 | $0.00007 | $0.00233 |
| Haiku 4.5 | $0.00004 | $0.00116 |
Grade A, and why
evidence-handling 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Handling
Evidence is not memory. This skill covers every Evidence/ area, what goes where, what rules apply, and how to keep evidence from polluting curated memory.
Evidence areas and their rules
agent-knowledge/
Evidence/
raw/ <- unprocessed extracted material (git log, file dumps, scan output)
imports/ <- cleaned or processed imported content (docs, web pages)
captures/ <- automatic event stream (sync, update, ship events)
Outputs/ <- generated views (indexes, HTML export, dashboards)
treated like evidence: non-canonical, regeneratable
All evidence is non-canonical. None of it is ever auto-promoted into Memory/. Outputs are also non-canonical.
Evidence/raw/
Use for:
- Raw git log extracts
- Unprocessed file dumps
- Raw command output
- Unfiltered scan results
Rules:
- Keep files small; trim or paginate large outputs
- Add a YAML frontmatter block with
note_type: evidence,source, andextractedtimestamp - Do not edit raw evidence after creation; create a new file instead
- Filename convention:
<topic>-<YYYY-MM-DD>.mdor the auto-generated git-recent.md
Template:
---
note_type: evidence
source: git-log
extracted: 2025-01-15T14:00:00Z
---
# Raw: Git Log (2025-01-15)
(content)
Evidence/imports/
Use for:
- Web pages imported via
bedrock clean-import - Documentation imported from external sources
- Third-party reference material
- Cleaned-up versions of raw evidence
Rules:
- Always mark with
note_type: evidenceandcanonical: false - Include
source:andimported:in frontmatter - Prefer cleaned markdown over raw HTML
- Do not include entire large docs -- trim to the relevant sections
- Use
bedrock clean-import <url>to create well-structured imports
Template:
---
note_type: evidence
source: https://docs.example.com/api-reference
imported: 2025-01-15T14:00:00Z
canonical: false
---
# Imported: API Reference (2025-01-15)
(cleaned content)
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 · 175 lines · 36 tokens per session scan A 1223f50354f1
evidence-handling is a skill published in the GitHub repository robotaitai/project-bedrock (45 stars, last pushed 21d ago), licensed MIT. It adds 36 tokens to every session and 1,163 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 2026-08-30.
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.