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 skills/samzong/agent-brains/agent-loadernpx skills add samzong/agent-brains --skill agent-loadergit clone --depth 1 https://github.com/samzong/agent-brainsWrote 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/samzong/agent-brains/agent-loader)<a href="https://agentmods.dev/skills/samzong/agent-brains/agent-loader"><img src="https://agentmods.dev/badge/skills/samzong/agent-brains/agent-loader.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00906 |
| Opus 5 | $0.00025 | $0.00453 |
| Sonnet 5 | $0.00010 | $0.00181 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
agent-loader 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 4d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Loader
Use this skill to list and load agent brains from two scopes:
REPO: $CWD/.agents/agents up to $REPO_ROOT/.agents/agents
USER: $HOME/.agents/agents
Repo scope is searched from the current working directory upward to the repository root. User scope is searched after repo scope. If the same agent name exists in multiple places, the first discovered agent wins.
For a global setup, clone this repository to ~/.agents/agent-brains, then symlink ~/.agents/agents to ~/.agents/agent-brains/agents.
The discovery roots can be overridden with AGENT_BRAINS_ROOT or the script's --root option. Overrides use custom scope.
Modes
List Agents
Use when the user asks what agents exist, asks for agent names, or is unsure which agent to load.
Run the bundled script:
uv run python skills/agent-loader/scripts/list_agents.py
Report each agent's name, description, scope, and path. Discovery only reads AGENTS.md frontmatter; it does not read the body or any other core file. If an agent has no description, say so directly.
List Workflows
Use when the user asks what workflows an agent has, or when loading an agent and a lightweight workflow summary is useful.
Run:
uv run python skills/agent-loader/scripts/list_agents.py --agent <name> --workflows
The script resolves <name> through the same repo/user discovery order, then reads only each workflow's WORKFLOW.md frontmatter. Report each workflow's name, description, and path. Do not read workflow bodies just to list workflows.
Load An Agent
Use when the user names an agent or asks to start working as an agent.
First resolve the agent path:
uv run python skills/agent-loader/scripts/list_agents.py --agent <name>
The script prints:
name<TAB>description<TAB>scope<TAB>path
For the resolved path, read in this order:
path/AGENTS.mdpath/SOUL.mdpath/MEMORY.md
Then acknowledge the active agent and summarize:
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.
- 4d ago First seen · 102 lines · 50 tokens per session scan A f6f17156c0d5
agent-loader is a skill published in the GitHub repository samzong/agent-brains (6 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 906 once invoked, about $0.0003 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 skills, from other repositories
onboard-repository
Inspect an unfamiliar or brownfield repository, trace one real operational path, and propose evidence-backed improvements that help future agents work independently. Use when explicitly asked to onboard, map, assess, or backfill agent-facing repository guidance; use again after the user approves exact proposal items.…
audit-onboarding-proposal
Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…
engineering-wisdom
Provide an explicitly requested, repository-grounded engineering review using contextual heuristics for code clarity, SOLID and design, testing, refactoring, architecture, and professional practice. Use only when the user invokes $engineering-wisdom or explicitly asks for this installed engineering-wisdom pack; do not…
improve-harness
Run one explicitly authorized, evidence-backed improvement to a repository's agent guidance, tools, runbooks, or validation. Use only when the user invokes $improve-harness or explicitly asks to improve the Harness after observed reusable agent friction. Do not use for ordinary product changes, speculative cleanup…
encode-invariant
Convert accepted repository rules into the smallest repository-native mechanical validation with positive and negative proof and precise enforcement-level reporting. Use for requests to enforce architecture, reliability, security, or quality boundaries; prevent a documented violation from recurring; add structural…
steadyagent-workflow
Local-first Codex workflow for planning, debugging, reviewing, refactoring, improving AGENTS.md, building skills, publishing agent harness repositories, or running complex multi-step coding tasks that need staged diagnosis, context control, verification loops, review strategy, release evidence, and…