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/spearchucker667/kimiko/agents-mdgit clone --depth 1 https://github.com/spearchucker667/kimikoWrote 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/instructions/spearchucker667/kimiko/agents-md)<a href="https://agentmods.dev/instructions/spearchucker667/kimiko/agents-md"><img src="https://agentmods.dev/badge/instructions/spearchucker667/kimiko/agents-md.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 | $0.01096 | $0.01096 |
| Opus 5 | $0.00548 | $0.00548 |
| Sonnet 5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
kimiko 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 6d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kimiko Context
Auto-Generated: 2026-07-29 | Primary Sources: Makefile, README.md, validator/requirements.txt, scripts/activate-mandate.sh, docs/AGENTS.md
Recent Update: Updated model configuration to Kimi K3.7 (
current_model = "kimi-k3.7", 1M token context window, 65536 max output tokens, native multimodal) inconfig/config.tomlandconfig/kimi.toml; seedocs/CHANGELOG.md.
1. System Identity
| Attribute | Value | Source |
|---|---|---|
| Language | Python (3.11+), Shell, PowerShell, Make | Source: README.md:L46-L64 |
| Runtime | Python, Bash, PowerShell | Source: README.md:L44-L64 |
| Framework | — | Source: — |
| Package Manager | pip | Source: validator/requirements.txt |
| Build System | Make | Source: Makefile:L1-L3 |
2. Operational Commands
| Intent | Command (Exact) | Working Dir | Notes | Source |
|---|---|---|---|---|
| Install | make install |
Root | Platform-aware installation | Source: Makefile:L169-L183 |
| Test | make test |
Root | Runs pytest suite for validator | Source: Makefile:L366-L373 |
| Validate | make check |
Root | Validates configuration | Source: Makefile:L341-L357 |
| Verify | make verify |
Root | Checks installation files | Source: Makefile:L375-L437 |
| Uninstall | make uninstall |
Root | Removes Kimiko-managed files | Source: Makefile:L327-L334 |
| Deps | make deps |
Root | Installs Python dependencies | Source: Makefile:L337-L339 |
3. Architecture & Conventions
| Concern | Value | Source |
|---|---|---|
| Entrypoint / Bootstrap | scripts/launch-with-mandate.sh |
Source: Makefile:L282; docs/AGENTS.md:L189-L194 |
| Routing | — | Source: — |
| State Management | kimi.json and config files deployed to ~/.kimi-code/ |
Source: docs/AGENTS.md:L245-L251 |
| Styling | — | Source: — |
| Testing | pytest |
Source: validator/requirements.txt:L3; Makefile:L372 |
| Linting / Formatting | ruff |
Source: validator/requirements.txt:L4 |
| Error Handling / Logging | Session logs in ~/.kimi-code/logs/ |
Source: docs/AGENTS.md:L39-L40 |
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.
- 6d ago First seen · 60 lines · 1,096 tokens per session scan A 18f2d6985662
kimiko AGENTS.md is an instructions file published in the GitHub repository spearchucker667/kimiko (140 stars, last pushed 1mo ago), licensed MIT. It adds 1,096 tokens to every session, about $0.0055 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 instructions, from other repositories
sessionview AGENTS.md
AGENTS.md instructions for tyql688/sessionview, covering sessionview, commands, app / frontend, gates must pass under both feature sets: default (gui) and and --no-default-features --features headless.
eip-mcp AGENTS.md
AGENTS.md instructions for exploitintel/eip-mcp, covering eip-mcp-v3, boundary, correctness rules, protocol and verification.
Nday-Exploit-Plan AGENTS.md
AGENTS.md instructions for OracleNep/Nday-Exploit-Plan, covering ai agent 使用规则, 适用场景, 使用流程, 可信度标注 and 禁止事项.
chat_edit CLAUDE.md
Instructions for tt-a1i/chat_edit, covering claude.md, language preference, project background, skill 使用规范 and project overview.
sessionview CLAUDE.md
Claude Code instructions for tyql688/sessionview, a project described as: Browse, search, resume and manage your AI coding sessions in one local desktop app. (Claude Code, Codex, Gemini,OpenCode, Cursor, kimi).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.