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/zaventh/dotagents-standard-skill/dotagents-standardnpx skills add zaventh/dotagents-standard-skill --skill dotagents-standardgit clone --depth 1 https://github.com/zaventh/dotagents-standard-skillWrote 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/zaventh/dotagents-standard-skill/dotagents-standard)<a href="https://agentmods.dev/skills/zaventh/dotagents-standard-skill/dotagents-standard"><img src="https://agentmods.dev/badge/skills/zaventh/dotagents-standard-skill/dotagents-standard.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 5.1 | $0.00230 | $0.04123 |
| Opus 5 | $0.00115 | $0.02062 |
| Sonnet 5 | $0.00046 | $0.00825 |
| Haiku 4.5 | $0.00023 | $0.00412 |
Grade A, and why
dotagents-standard 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 5d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dotagents
What this is
dotagents turns a project's agent context from one big file into a router + a library.
- The router is a slim
AGENTS.mdat the repo root. It is always read. It describes the agent's identity and, crucially, tells the agent where to look for deeper context — but only when a task actually needs it. - The library is a hidden
.agents/directory holding the "heavy" context, split into small, single-purpose files organized by kind (behavioral rules vs. static reference vs. durable memory vs. task specs, etc.).
The whole point is progressive disclosure: load a screenful of routing rules up front, then
pull in only the specific files the current task matches. A monolithic AGENTS.md/CLAUDE.md
forces the agent to read a database schema while editing CSS, mixes "never use any" (a rule)
with "we chose Postgres in 2023" (a memory), and invites a clutter of vendor folders
(.claude/, .cursor/, .gemini/) in the root. dotagents fixes all three by separating by
kind and loading conditionally.
The value lives entirely in that discipline. If you dump everything into AGENTS.md, you've
gained nothing. If you scatter files but the router never points to them, agents won't find
them. Both halves — a tight router and well-factored files — must hold.
Two related specs share the ".agents" name
Be aware there are two overlapping standards; know which one the user means:
- dotagents (github.com/bgreenwell/dotagents, Draft 0.1.0) — the lean, hand-authored, project-scoped directory-as-context architecture described in this skill. This is "the dotagents standard" and the default subject here.
- The .agents Protocol (dotagentsprotocol.com, Draft) — a superset that keeps the same
.agents/idea but adds machine-readable config (mcp.json,models.json), a global~/.agents/layer that merges with the project layer, structured sub-agents / tasks / memories with frontmatter schemas, and a public "Hub" for sharing.dotagentsbundles.
What ships with it
8 files 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.
- 5d ago First seen · 289 lines · 230 tokens per session scan A 962f0037eb5e
dotagents-standard is a skill published in the GitHub repository zaventh/dotagents-standard-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 230 tokens to every session and 4,123 once invoked, about $0.0011 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
os-memory-manager
Trigger with "remember this", "update memory", "what should we record from this session", "capture learnings", "write a session log", or when closing a session. Guides agents on managing memory hygiene across sessions, deciding what to write to dated memory logs, what to promote to long-term memory.md, and when to…
os-improvement-loop
Pattern 5: Concurrent Event-Driven Multi-Agent Loop. Coordinates multiple Claude sessions as OS threads sharing a common event bus and memory address space. Every loop cycle is a full improvement cycle: execute, eval against benchmark (KEEP/DISCARD), emit friction events, and close with surveys, metrics, memory…
rlm-cleanup-agent
Removes stale and orphaned entries from the RLM Summary Ledger. Use after files are deleted, renamed, or moved to keep the ledger in sync with the filesystem. user: "Clean up the RLM cache after I renamed some files" assistant: "I'll use rlm-cleanup-agent to remove stale entries from the ledger." user: "The RLM ledger…
hf-upload
Upload primitives for HuggingFace Soul persistence - file, folder, snapshot, JSONL append, and dataset card management with exponential backoff. Use when persisting agent learnings, snapshots, or semantic caches to HuggingFace.
rlm-audit
Audit RLM cache coverage - compare manifest against filesystem.
notebook
Project notes system to prevent AI context loss and reasoning loops. Init notes, save mid-flow, recover context, migrate messy notes, resolve lessons. Subcommands: /notebook, /notebook save, /notebook recover, /notebook migrate.