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 instructions/milisp/keke-agent/agents-mdgit clone --depth 1 https://github.com/milisp/keke-agentWhat 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 | $0.01293 | $0.01293 |
| Opus 5 | $0.00647 | $0.00647 |
| Sonnet 5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
keke-agent AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
keke — agent guide
keke is a multi-vendor terminal coding agent. Vendor-specific behavior lives in replaceable plugins; the engine does not know that ChatGPT or Grok exist.
Read docs/architecture.md before making structural changes.
Invariants
These are not style preferences. Each one exists because a reference implementation lost it and paid for it.
-
Nothing vendor-specific in
keke-core. Nokeke-provider-*orkeke-auth-*dependency, no vendor name in a match arm. OpenAI's codex wrote "resist adding code to codex-core" in its own guide andcodex-corestill ended up depending on ~50 internal crates. Prose did not hold the line, soscripts/check-layering.pyholds it instead and runs in CI. -
Dependencies point strictly downward by rank. Contract crates (tier 0) depend on nothing above them and not on each other except in the documented order. Adding a crate means adding it to
RANKin the layering script. -
Contract crates stay dependency-light.
keke-protocol,keke-tool,keke-auth-api,keke-provider-api,keke-plugin-api,keke-config-types, andkeke-pathsmay useserde,futures,thiserror,schemars, and each other. No HTTP client, no runtime, no engine. This is what lets a vendor plugin authenticate without linking the world. -
RPITIT over
#[async_trait]. Writefn f(&self, ..) -> impl Future<Output = T> + Send. Where a trait must be held asdyn, box explicitly at that one boundary — seekeke_tool::ToolDynandkeke_plugin_api::ExtFuture. Do not reach for#[async_trait]. -
Registration returns a disposer, or is composed once and frozen. A registry either hands back something whose drop removes the contribution, or is a builder that produces an immutable value. A contribution must never be able to outlive the thing that made it.
-
Model-visible implies logged. Anything reaching a model request must be reconstructable from
SessionEvents. Adding a new kind of model-visible input means adding a variant tokeke_protocol::SessionEventfirst.
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 · 103 lines · 1,293 tokens per session scan A 6943e9d2871f
keke-agent AGENTS.md is an instructions file published in the GitHub repository milisp/keke-agent (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,293 tokens to every session, about $0.0065 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 instructions, from other repositories
sigma AGENTS.md
Instructions for hututuQQQ/sigma, covering agent instructions and benchmark fairness.
dsh-TUI AGENTS.md
AGENTS.md instructions for ccch1mneyyy/dsh-TUI, covering agents.md, 仓库布局, 命令, 上游边界与契约 and 约定与红线.
wispterm AGENTS.md
Instructions for xuzhougeng/wispterm, covering agents.md, architecture, ui presentation styles, cohesion and coupling and integration layer vs feature domains.
golembot CLAUDE.md
Instructions for 0xranx/golembot, covering golembot — project conventions for claude code, architecture hard constraints, things you must never do, interface change rules and file responsibility boundaries.
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).
superset CLAUDE.md
Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.