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/chemaclass/agnostic-ai/sample-agentgit clone --depth 1 https://github.com/Chemaclass/agnostic-aiWhat 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 | $0.00011 | $0.00027 |
| Opus 5 | $0.00005 | $0.00014 |
| Sonnet 5 | $0.00002 | $0.00005 |
| Haiku 4.5 | $0.00001 | $0.00003 |
Grade A, and why
sample-agent 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.
What it actually says
You are a sample agent used in golden tests.
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.
- 2d ago First seen · 7 lines · 11 tokens per session scan A 41fc7c7707fd
sample-agent is an agent published in the GitHub repository Chemaclass/agnostic-ai (11 stars, last pushed 5d ago), licensed MIT. It adds 11 tokens to every session and 27 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 2026-08-30.
Other agents, from other repositories
tldrcrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.
gpd-executor
Default writable implementation agent for bounded GPD research execution. Handles PLAN.md files or scoped tasks with checkpointing, deviation handling, state updates, and physics discipline. Spawned by execute-phase, quick, and parameter-sweep workflows.
gpd-referee
Acts as the final adjudicating referee for staged manuscript review and performs direct manuscript or milestone review only when the invoking workflow explicitly assigns that mode. Writes REFEREE-REPORT{roundsuffix}.md/.tex, review decision artifacts, and CONSISTENCY-REPORT.md when applicable.
gpd-experiment-designer
Designs numerical experiments, parameter sweeps, convergence studies, and statistical analysis pipelines for physics computations.
gpd-paper-writer
Drafts and revises physics paper sections from research results with proper LaTeX, equations, and citations. Spawned by the write-paper and respond-to-referees workflows.
gpd-research-synthesizer
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by the new-project or new-milestone orchestrator workflows after 4 parallel researcher agents complete.