collecting-evidence

collecting-evidence is a skill for Claude Code from synaptiai/synapti-marketplace. It costs 36 tokens per session (1,586 once invoked), scanned A, original, Apache-2.0.

A research skill for recording source-backed findings as structured YAML evidence files.

In plain words
What is it for?
Use it when investigating one research area and documenting its sources, claims, supporting data, and confidence.
Why use it?
It helps keep research claims traceable, while recording confidence levels and assumptions instead of relying on loose notes.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: agent in frontmatter; names the TodoWrite tool.

Part of the context-ledger plugin — 5 skills, 8 commands, 5 agents shipped together

Good fit Use it when investigating one research area and documenting its sources, claims, supporting data, and confidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synaptiai/synapti-marketplace/collecting-evidence
Install

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.

Any agent
npx skills add synaptiai/synapti-marketplace --skill collecting-evidence
Clone the repo
git clone --depth 1 https://github.com/synaptiai/synapti-marketplace

Made for: Claude Code.

Or install context-ledger, the plugin that ships this one along with the rest of its 5 skills, 8 commands, 5 agents.

Wrote 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.

agentmods badge for collecting-evidence

README.md
[![agentmods](https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/collecting-evidence/github.svg)](https://agentmods.dev/skills/synaptiai/synapti-marketplace/collecting-evidence)
Your own site
<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.

agentmods 80×15 button for collecting-evidence

Your own site · 80×15
<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>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,586 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash d5d3bb558e8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

plugins/context-ledger/skills/collecting-evidence/SKILL.md · 229 lines

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-init completed)
  • 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:

  1. Extract the key claim(s)
  2. Note supporting quotes/data
  3. Assess confidence level
  4. 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.

Read the full file on GitHub · 229 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 229 lines · 36 tokens per session scan A d5d3bb558e8c

Subscribe to this mod's changes

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.