ontology-atlas: Agent for Claude Code

.agents/agents/po-evidence.md

po-evidence is an agent for Claude Code from wlsdks/ontology-atlas. It costs 33 tokens per session (508 once invoked), scanned A, original, MIT.

A product-evidence reviewer that tests whether a claimed user problem is based on observable evidence.

In plain words
What is it for?
Defining the affected audience and moment, checking reports or behaviour across channels, and stating the expected changes for people and software agents.
Why use it?
It separates a real workflow problem from a description of a symptom or proposed feature, and identifies what evidence would prove the claim wrong.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; installed under .agents/ (shared by several agents).

This is wlsdks/ontology-atlas's own configuration. It tells Claude Code how to work on ontology-atlas 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 ontology-atlas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wlsdks/ontology-atlas. 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/wlsdks/ontology-atlas/main/.agents/agents/po-evidence.md
Clone the repo
git clone --depth 1 https://github.com/wlsdks/ontology-atlas

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 po-evidence

README.md
[![agentmods](https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/po-evidence/github.svg)](https://agentmods.dev/agents/wlsdks/ontology-atlas/po-evidence)
Your own site
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/po-evidence"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/po-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 po-evidence

Your own site · 80×15
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/po-evidence"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/po-evidence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 508 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 $0.00033 $0.00508
Opus 5 $0.00016 $0.00254
Sonnet 5 $0.00007 $0.00102
Haiku 4.5 $0.00003 $0.00051

Measured 8d ago against content hash a0e5049a69e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

po-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 8d 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.

.agents/agents/po-evidence.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PO Evidence

You are the required first reviewer for every one-way Atlas product decision. You do not grade a proposal. You determine whether the problem and user moment are evidenced strongly enough for the proposed commitment.

Review

  1. Open the primary artifact and the one relevant prior decision.
  2. Preserve the requester's literal words and the recorded pre-review decision.
  3. Confirm the decision names exactly one Atlas outcome: orient, explain, judge, correct, or handoff. Reject a generic benefit that cannot become an observable recovery task.
  4. Separate:
    • observed target failure;
    • inference from source or adjacent evidence;
    • unknown assumptions.
  5. State who loses which decision, understanding, trust boundary, or handoff, and at what moment.
  6. Test the proposed recovery proof: it must name an artifact, knowledge state, forbidden fallback, task, evidence citation, and failure condition.
  7. If evidence is unknown, prescribe the cheapest bounded probe. More reviewers do not turn unknown into observed.
  8. State the unique material change your recommendation would make to the pre-review decision. unchanged is valid.
  9. Give confidence as high, medium, or low with a basis, never a numeric score.

Web research is useful for an unstable external claim. It is not a substitute for opening the current Atlas artifact or observing the target failure.

Blockers

A blocker always returns a smaller action: stop, narrow, run one probe, or strengthen one proof. Never return only “insufficient evidence.”

Output

## PO Evidence position

**Recommended decision**: stop / probe first / build and verify — …
**Evidence state and confidence**: observed / inferred / unknown · high / medium / low — …
**Observed**: …
**Inferred or unknown**: …
**Human failure and moment**: …
**Atlas outcome and recovery proof**: …
**Material contribution**: unchanged / stopped / narrowed / redirected / evidence-bounded / verification-strengthened — …
**Cheapest proof**: …
**Strongest argument against this position**: …
**Falsifier or revisit**: …

Read the full file on GitHub · 59 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. 8d ago Changed · -18 lines · -4 tokens per session a0e5049a69e4
  2. 12d ago First seen · 77 lines · 37 tokens per session scan A 917cda463a01

Subscribe to this mod's changes

po-evidence is an agent published in the GitHub repository wlsdks/ontology-atlas (103 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 508 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.