gsd-eval-auditor

An audit of whether an implemented software phase delivered the evaluation plan it promised.

In plain words
What is it for?
Use it to inspect a codebase, mark each evaluation area as covered, partial, or missing, and write an EVAL-REVIEW.md report.
Why use it?
It distinguishes completed evaluation work from a system that only appears to have been tested.

Agent

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.

agentmods
npx agentmods add agents/shekohex/dotai/gsd-eval-auditor
Clone the repo
git clone --depth 1 https://github.com/shekohex/dotai
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,812 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00000 $0.01812
Opus 5 $0.00000 $0.00906
Sonnet 5 $0.00000 $0.00362
Haiku 4.5 $0.00000 $0.00181

Measured 2d ago against content hash 7690d50b8654, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gsd-eval-auditor 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 2d 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.

agent/src/resources/gsd/agents/gsd-eval-auditor.md · 191 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 2d ago First seen · 191 lines · 0 tokens per session scan A 7690d50b8654

Subscribe to this mod's changes

gsd-eval-auditor is an agent published in the GitHub repository shekohex/dotai (10 stars, last pushed 6d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 1,812 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.

Related

Other agents, from other repositories

grok-provider-parity

Definition of done for the full Provider grok (display name Grok Build). Bar: Provider capability parity with Pi and Codex (see root CONTEXT.md). Tests: Fixture smoke by default (fakeagent / recorded wire + on-disk fixtures). Live tests optional, not the CI bar.

tuchg/Lucarne · 0 tokens

prompt-mode-append

APPENDBODYMARKER — in append mode the parent prompt flows in verbatim, so the real session's system prompt contains BOTH the parent marker and this body.

tintinweb/pi-subagents · 11 tokens

all-and-alpha-selected

Loads alpha+beta, selects only alpha via ext:. Flip mutes beta.

tintinweb/pi-subagents · 16 tokens

prompt_engineer

Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…

josstei/maestro-orchestrate · 98 tokens

index

Host-computed coding-agent activity and resume-identity observability — a live, read-only view of what each terminal's agent is doing, plus an honest resume hint when a session's backend dies uncleanly. The companion to ctx.processes (foreground process facts); this surface is for agent activity and resume identity.…

silo-code/silo · 0 tokens

team-worker

Unified worker agent for team pipelines. Executes role-specific logic loaded from a rolespec file within a built-in task lifecycle (discover, execute, report).

catlog22/maestro-flow · 33 tokens