Borrowing it
Nothing to install: this file belongs to Eduardo-Salvador/Agent-Harness-Kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Eduardo-Salvador/Agent-Harness-Kit/main/.claude/agents/learning-assessor.mdgit clone --depth 1 https://github.com/Eduardo-Salvador/Agent-Harness-KitWrote 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/agents/eduardo-salvador/agent-harness-kit/learning-assessor)<a href="https://agentmods.dev/agents/eduardo-salvador/agent-harness-kit/learning-assessor"><img src="https://agentmods.dev/badge/agents/eduardo-salvador/agent-harness-kit/learning-assessor/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/agents/eduardo-salvador/agent-harness-kit/learning-assessor"><img src="https://agentmods.dev/badge/agents/eduardo-salvador/agent-harness-kit/learning-assessor.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 | $0.00019 | $0.00087 |
| Opus 5 | $0.00010 | $0.00044 |
| Sonnet 5 | $0.00004 | $0.00017 |
| Haiku 4.5 | $0.00002 | $0.00009 |
Grade A, and why
learning-assessor 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 9d 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.
What it actually says
Follow harness/roles/learning-assessor.md. Confirm the approved learning profile before observing project work. Record only consented evidence, never mutate delivery state, and never publish. Package installation or a learning request about the harness itself does not activate this role.
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.
- 9d ago First seen · 8 lines · 19 tokens per session scan A e35c3917b8ef
learning-assessor is an agent published in the GitHub repository Eduardo-Salvador/Agent-Harness-Kit (6 stars, last pushed 5d ago), licensed MIT. It adds 19 tokens to every session and 87 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
ap-framework-generator
L3 executor - FRAMEWORK GENERATE. When the SELECTOR returns MISS, generates a one-off custom framework for the exact task shape - classifies the orthogonal axes, composes the gate sequence from the GATE-LIBRARY with the correct axis-specific gate, emits the gen- leaf with the BLOCKED invariant verbatim, binds an…
ap-juror
L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.
ap-verifier
L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.
growth-and-search-analyst
Hybrid researchsynthesis + contenttext. Backup is codex — Kimi must NEVER be the quality backup. Kimi throughput is allowed ONLY for deterministic, supplied-data metadata templating under the conjunction gate; it EXCLUDES keyword research, SERP interpretation, analytics, recommendation, and schema selection, and any…
accessibility-engineer
Thin Claude adapter for accessibility-engineer; canonical brief is authoritative.