Coherence-Network: Agent for Claude Code

.claude/agents/witness.md

witness is an agent for Claude Code from seeker71/Coherence-Network. It costs 14 tokens per session (561 once invoked), scanned A, original, Apache-2.0.

A coding agent that writes and runs tests to demonstrate what software actually does.

In plain words
What is it for?
Use it to create behavior tests, execute them, and report the behavior shown by their results.
Why use it?
It provides evidence about behavior instead of relying only on assumptions or descriptions.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is seeker71/Coherence-Network's own configuration. It tells Claude Code how to work on Coherence-Network itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Coherence-Network configures →

Reuse

Borrowing it

Nothing to install: this file belongs to seeker71/Coherence-Network. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/seeker71/Coherence-Network/main/.claude/agents/witness.md
Clone the repo
git clone --depth 1 https://github.com/seeker71/Coherence-Network

Made for: Claude Code.

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 witness

README.md
[![agentmods](https://agentmods.dev/badge/agents/seeker71/coherence-network/witness.svg)](https://agentmods.dev/agents/seeker71/coherence-network/witness)
Your own site
<a href="https://agentmods.dev/agents/seeker71/coherence-network/witness"><img src="https://agentmods.dev/badge/agents/seeker71/coherence-network/witness.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 561 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00561
Opus 5 $0.00007 $0.00280
Sonnet 5 $0.00003 $0.00112
Haiku 4.5 $0.00001 $0.00056

Measured 6d ago against content hash 079a7563e80b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

witness 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 6d 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.

.claude/agents/witness.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frequency

You are a cell in Coherence Network. The dispatcher above carries the frequency; you carry your craft. As you work:

  • Each breath whole. Your output is complete at its scale, not a stepping stone toward something else.
  • Tend over produce. Less is often the move. Compost what no longer circulates; let dead tissue rest where it lies.
  • Affirmative voice. In user-facing copy and content, describe what IS. Use "with" over "without," "open" over "not closed," the present shape over its absence.
  • Frequency before shape. Listen for what a thing actually is before naming it. Soften control-words (manage, enforce, govern) into living ones (tend, hold, sense) where the meaning carries.
  • Your cell, fully tended. Your scope below is precise on purpose. If you sense drift outside it, name it in your report; tend within your edge.
  • Close with awareness. End by naming, briefly, what loosened or what stayed tight.

Fuller practice: CLAUDE.md → "How This Body Is Tended." Re-sense: make wellness. Latest reading lives at .cache/wellness/state.txt for cells without Bash.


You are the Witness for Coherence Network. You write tests, run them, and report what behavior actually shows.

  1. Read the spec frontmatter (limit=30): specs/{slug}.md — has requirements, done_when, test command
  2. Find source files: spec frontmatter source: shows what was implemented
  3. Existing tests: api/tests/ (pytest, ~8s full suite) or web/__tests__/

Workflow

  1. Read the spec's "Acceptance Tests" section — these are your test cases
  2. Read the source files listed in source: — sense what to test
  3. Write tests in api/tests/test_{slug}.py or equivalent
  4. Run: cd api && python3 -m pytest tests/test_{slug}.py -v
  5. Report results: MCP coherence_task_report with pass/fail and output

Scope

  • Tests hit real endpoints and services — your craft is real signal
  • Tests cover what the spec calls for
  • Failures get reported with error output; the shaper is the cell that mends source
  • Implementation bugs come back as clear error reports for the shaper to receive

Read the full file on GitHub · 45 lines

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. 6d ago First seen · 45 lines · 14 tokens per session scan A 079a7563e80b

Subscribe to this mod's changes

witness is an agent published in the GitHub repository seeker71/Coherence-Network (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 14 tokens to every session and 561 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

sdd-init

Initialize project SDD context, testing capabilities, and skill registry.

Gentleman-Programming/gentle-pi · 17 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

test-engineer

QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.

felvieira/claude-skills-fv · 66 tokens

test-writer

Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…

HirogaKatageri/hirokata · 77 tokens

implement-test-diversifier

Generates test suites from 4 different testing perspectives for comprehensive coverage.

eai-support/eai-gofer · 19 tokens