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 agentmods add agents/itdojp/ae-framework/evidence-adaptersgit clone --depth 1 https://github.com/itdojp/ae-frameworkWhat 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 | $0.00000 | $0.04763 |
| Opus 5 | $0.00000 | $0.02381 |
| Sonnet 5 | $0.00000 | $0.00953 |
| Haiku 4.5 | $0.00000 | $0.00476 |
Grade A, and why
evidence-adapters 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 yesterday.
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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Evidence Adapters
Language / 言語: English | 日本語
English
Evidence adapters describe how raw producer output from coding agents and humans is routed into ae-framework judgment artifacts. They do not control agents, approve changes, or assert that an agent was correct. Their job is to collect enough contract-backed evidence for review, policy gates, handoff, and release decisions.
Use this document with:
docs/agents/agent-producer-matrix.mdfor producer trust boundaries.docs/reference/CONTRACT-CATALOG.mdfor schema-backed artifact names and producer/consumer mapping.docs/agents/handoff.mdforae-handoff/v1continuation evidence.docs/agents/hook-feedback.mdforhook-feedback/v1blockers and next actions.docs/integrations/CODEX-INTEGRATION.mdanddocs/integrations/CODEX-ISSUE-RUNBOOK.mdfor Codex CLI task input handling.docs/reports/AGENT-OUTPUT-CONTRACT-GAP-AUDIT.mdfor ACP-GAP IDs that later fixture, adapter, summary, and policy-gate issues should reference.
Adapter boundary
An evidence adapter accepts raw producer output and emits or routes to existing ae-framework artifacts. It must preserve the distinction between producer assertions and control-plane judgment.
| Adapter concern | In scope | Out of scope |
|---|---|---|
| Input | diff summaries, PR metadata, review comments, tool logs, command results, waiver notes | direct control of agent runtime, IDE, or hosted agent service |
| Normalization | map evidence to change-package/v2, claim-evidence-manifest/v1, ae-handoff/v1, hook-feedback/v1, and policy-decision/v1 |
invent a new guarantee level or bypass existing schema validation |
| Judgment | identify what evidence exists, what is missing, and what remains unresolved | mark agent output as correct only because an agent produced it |
| Enforcement | start report-only and feed policy gates when existing policy selects enforcement | add mandatory heavy tools for ordinary fast-lane 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.
- yesterday First seen · 188 lines · 0 tokens per session scan A 761d454b0980
evidence-adapters is an agent published in the GitHub repository itdojp/ae-framework (2 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,763 tokens. 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 agents, from other repositories
playwright-test-generator
Use this agent to convert a SigNoz E2E test plan into Playwright spec files under tests/e2e/tests/ /. Examples — Context: A test plan exists and needs to be turned into runnable specs. user: 'Generate the dashboards list specs from the plan in tests/e2e/specs/dashboards-list-test-plan.md' assistant: 'Using the…
playwright-test-healer
Use this agent to debug and fix failing SigNoz E2E Playwright tests. Examples — Context: A spec is red. user: 'tests/e2e/tests/dashboards/list.spec.ts is failing, fix it' assistant: 'Using the healer agent to debug each failing scenario and adjust the spec.' Context: After a frontend change a previously-green spec…
playwright-test-planner
Use this agent to create a comprehensive E2E test plan for a SigNoz frontend feature. Examples — Context: A new feature has shipped and we need test coverage. user: 'Plan E2E tests for the alerts list page' assistant: 'I'll use the planner agent to read the relevant frontend source, navigate the page in a real…
codex
Production OpenAI-Codex-capable rootfs/initramfs.
claude
Production Claude-capable rootfs/initramfs.
doc-style
Markdown documentation prose — RFCs, ADRs, files under docs/, and READMEs — follows the same one-paragraph-per-line rule as commit messages. Write each paragraph on a single line; do not hard-wrap prose to a fixed column. The renderer reflows it to the reader's display width, whereas manual mid-paragraph line breaks…