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 synaptiai/synapti-marketplace --skill collecting-evidencegit clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote 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/synaptiai/synapti-marketplace/collecting-evidence)<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/collecting-evidence"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/collecting-evidence/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/synaptiai/synapti-marketplace/collecting-evidence"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/collecting-evidence.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 | $0.00036 | $0.01586 |
| Opus 5 | $0.00018 | $0.00793 |
| Sonnet 5 | $0.00007 | $0.00317 |
| Haiku 4.5 | $0.00004 | $0.00159 |
Grade A, and why
collecting-evidence 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Collection
This skill guides the creation of structured Evidence Objects for a single research pillar.
Prerequisites
- Ledger workspace initialized (
/ledger-initcompleted) - Pillar assignment (which pillar to research)
- Research scope from
01-pillars/PILLARS.md
Workflow
Use TodoWrite to track these mandatory steps:
Step 1: Load Pillar Scope
Read 01-pillars/PILLARS.md to understand:
- Pillar priority level
- Specific research questions for this pillar
- Any scope restrictions
See references/research-protocols.md for pillar-specific protocols.
Step 2: Identify Evidence Sources
For each research question, identify potential sources:
| Source Type | Examples | Typical Confidence |
|---|---|---|
url |
Research reports, documentation | 60-90 |
pdf |
Academic papers, whitepapers | 70-95 |
interview |
User interviews, expert calls | 50-80 |
internal-doc |
Company data, prior research | 60-85 |
experiment |
A/B tests, prototypes | 70-95 |
dataset |
Analytics, survey results | 65-90 |
Step 3: Collect Raw Evidence
For each source:
- Extract the key claim(s)
- Note supporting quotes/data
- Assess confidence level
- List assumptions
Web research protocol:
- Use WebSearch for discovery
- Use WebFetch to retrieve and analyze content
- Track source URLs and retrieval dates
- Note if sources agree or contradict
Step 4: Create Evidence Objects
Write YAML files to 02-evidence/<pillar>/.
Naming: Use semantic IDs per references/id-generation-rules.md.
Schema: See references/evidence-object-schema.md.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 229 lines · 36 tokens per session scan A d5d3bb558e8c
collecting-evidence is a skill published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 1,586 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
create-or-update-concepts
Scan and analyze the project codebase to create or update concept files in agents-context/concepts/ (organized by domains/, source/, shared/) and update the README index and Load-When Cheatsheet.
step2-scope-tasks
Break a specification into ordered task groups with explicit context-awareness directives.
step1-write-spec
Gather requirements through structured Q&A, then formalize into a specification document.
create-pr
Creates a GitHub Pull Request on the current branch with a description focused on WHAT changed (not HOW). Uses emojis in the title and description. Use when the user asks to create a PR, open a pull request, or submit changes for review. Triggers on mentions of PR, pull request, merge request, or code review.
plan-product
Define product mission, vision, target users, and technology stack.
step4-archive-spec
Archive a completed spec — moves it to specs-archived and blocks agent access.