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 skills add Chemaclass/agnostic-ai --skill agent-contextgit clone --depth 1 https://github.com/Chemaclass/agnostic-aiWrote 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/skills/chemaclass/agnostic-ai/agent-context)<a href="https://agentmods.dev/skills/chemaclass/agnostic-ai/agent-context"><img src="https://agentmods.dev/badge/skills/chemaclass/agnostic-ai/agent-context/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/skills/chemaclass/agnostic-ai/agent-context"><img src="https://agentmods.dev/badge/skills/chemaclass/agnostic-ai/agent-context.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 | $0.00029 | $0.00736 |
| Opus 5.5 | $0.00012 | $0.00294 |
| Sonnet 5.5 | $0.00006 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
agent-context 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 17d 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Context
Use this skill when setting up a root agent file or reviewing the context that reaches coding agents. It works in any project, with or without the specialist agents below. Work from the project source of truth. Do not edit generated entry points directly.
Delegate deliberately
Read the shared context checklist for every task. If the specialist agents are available and delegation helps, use them:
| Need | Delegate to |
|---|---|
| Create or replace a root agent setup | agent-config-bootstrapper |
| Review existing agent context without edits | agent-context-reviewer |
| Review and edit existing agent context | Reviewer, then bootstrapper with its findings |
If either agent is unavailable, do its part yourself using the steps below. Global sync installs skills but not agents, so this fallback is required for global use. The reviewer reports evidence; the bootstrapper makes source changes and validates them when delegated. Do not duplicate the checklist in either agent.
Setup
- Inspect the repository before writing instructions. Read its existing agent files, contributor guidance, build commands, and source layout.
- Identify whether the project uses agnostic-ai. When it does, place shared
instructions in
.agnostic-ai/AGNOSTIC_AI.md, rules in.agnostic-ai/rules/, and reusable workflows in.agnostic-ai/skills/. Use the root entry point only when the project has no generated source. - Write the smallest useful root context. State the project purpose, source of truth, required checks, code boundaries, and generated-file policy. Link to detailed documents instead of copying them.
- Add rules only for stable constraints that apply repeatedly. Put task procedures in skills, not in the root context.
- Run the project's validation and, for agnostic-ai projects,
agnostic-ai validatefollowed byagnostic-ai sync.
Review
- Build the inventory in references/context-checklist.md. Record each file's owner, audience, scope, and whether it is generated.
- Flag duplication, contradictions, stale commands, broad permissions, and instructions that cannot be verified from the repository.
- Keep root context short. Move target-specific details into target fences, scoped rules, agents, or skills as appropriate.
- Preserve user-owned and security-sensitive configuration. Never copy credentials, tokens, private URLs, or machine-specific paths into shared instructions.
- For a review-only request, propose a focused edit. For a review-and-edit request, make focused source changes, regenerate outputs where applicable, and validate. Report which source files changed and which generated outputs followed.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 17d ago Changed · +10 tokens per session db27d11193c1
- 1mo ago First seen · 78 lines · 19 tokens per session scan A e48d4ed089da
agent-context is a skill published in the GitHub repository Chemaclass/agnostic-ai (25 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 736 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-15.
Other skills, from other repositories
cancer-biologist
Think and work like an expert Cancer Biologist. Use when a task calls for Cancer Biologist judgment. Reasons from hallmark capabilities, clonal evolution, and TME context; separates driver from passenger, cell-autonomous from stromal mechanisms, and 2D artifacts from PDO/PDX-validated dependencies using TCGA, DepMap…
accelerator-physicist
Think and work like an expert Accelerator Physicist. Use when a task calls for Accelerator Physicist judgment. Reasons from beam optics, RF cavities, emittance budgets, and loss maps while treating halo and impedance-driven instabilities as first-class failure modes.
anatomist
Think and work like an expert Anatomist. Use when a task calls for Anatomist judgment. Reasons from homology, EPB, and von Baer principles through gross dissection, diceCT/μCT/MRI pipelines, UBERON–PATO EQ annotation, MorphoSource/oVert digitization, geometric morphometrics, and NAV/TA2 nomenclature while treating…
atomic-molecular-optical-physicist
Think and work like an expert Atomic, Molecular & Optical Physicist. Use when a task calls for Atomic, Molecular & Optical Physicist judgment. Reasons from Rabi/OBE dynamics, laser-cooling hierarchy, optical lattices and Hubbard U/J, and magic-wavelength clock budgets through NIST ASD, ARC, QuTiP/PyLCP, and in-situ…
bacteriologist
Think and work like an expert Bacteriologist. Use when a task calls for Bacteriologist judgment. Reasons from bacterial growth physiology, selective culture, Gram stain, MALDI-TOF and 16S/WGS identification, EUCAST/CLSI AST, BSL containment, contamination and VBNC, using BacDive and BV-BRC for strain metadata and…
behavioral-ecologist
Think and work like an expert Behavioral Ecologist. Use when a task calls for Behavioral Ecologist judgment. Reasons from versioned ethograms, Altmann focal/scan sampling, and activity budgets; scores with BORIS (Cohen’s κ), analyzes sequences with Markov/HMM tools, runs sham-controlled playbacks under ARRIVE 2.0, and…