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/kanevry/session-orchestrator/claude-mdgit clone --depth 1 https://github.com/Kanevry/session-orchestratorWrote 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/kanevry/session-orchestrator/claude-md)<a href="https://agentmods.dev/instructions/kanevry/session-orchestrator/claude-md"><img src="https://agentmods.dev/badge/instructions/kanevry/session-orchestrator/claude-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 | $0.03554 | $0.03554 |
| Opus 5 | $0.01777 | $0.01777 |
| Sonnet 5 | $0.00711 | $0.00711 |
| Haiku 4.5 | $0.00355 | $0.00355 |
Grade A, and why
session-orchestrator CLAUDE.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 yesterday.
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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Orchestrator Plugin
Project-instruction file resolution: this is
CLAUDE.mdon Claude Code / Cursor IDE; the equivalent file on Codex CLI isAGENTS.md. See skills/_shared/instruction-file-resolution.md.
Lean root by design (Anthropic large-codebase best-practice: root = pointers + critical gotchas). Delegated docs:
- Install, CLI usage, architecture, component inventory →
README.md(§Components)- Sub-agent authoring spec (frontmatter, body,
sandbox-tier,output-schema) →agents/AGENTS.md- Stable product/tech/structure context →
.orchestrator/steering/(injected at session-start Phase 2.6)- Always-on + path-scoped rules →
.claude/rules/(per-wave viarule-loader.mjs, #336/#694); authoring spec →docs/rule-authoring.md- Session narrative & decisions log → [[01-projects/session-orchestrator/decisions]] in the Meta-Vault
- Operator tmux side-channel →
/tmux-layout(4-pane: STATE.md/CI-watch/events; ADR-0007)Additive instruction-file layering: this root for the big picture, nested files (
agents/AGENTS.md,.claude/rules/*.md) for local conventions.
Current State
State-free by design (see the Live state is not in this file gotcha below). The live version, test/coverage counts, backlog, and component inventory live in their SSOTs — never inline here, because they drift faster than this file is edited:
- Version + test/coverage → README badges
- Per-session metrics & history →
.orchestrator/metrics/sessions.jsonl - Session narrative & decisions → [[01-projects/session-orchestrator/decisions]] (Meta-Vault)
Critical Gotchas
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.
- yesterday First seen · 220 lines · 3,554 tokens per session scan A b7d6079b1840
session-orchestrator CLAUDE.md is an instructions file published in the GitHub repository Kanevry/session-orchestrator (49 stars, last pushed yesterday), licensed MIT. It adds 3,554 tokens to every session, about $0.0178 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 2026-09-03.
Other instructions, from other repositories
semantix CLAUDE.md
Claude Code instructions for Gnosil/semantix, covering 项目规则（claude code）, 1. 改动须经用户过目；由 claude 提交到分支 + pr，用户 review 后合并 and 2. 本地实验区：论文数据与实验材料不进 github.
rimz AGENTS.md
AGENTS.md instructions for rimio-ai/rimz, covering agents.md, how to read this contract, engineering principles, product invariants and room quick reference.
rimz CLAUDE.md
Claude Code instructions for rimio-ai/rimz, a project described as: RimZ is a realtime dashboard and control room for harnessing agentic coding, build on tmux and Zellij.
open-bridge AGENTS.md
Instructions for bks-lab/open-bridge, covering the bridge — agent instructions, required reading, session start detection (automatic), theme and agents.
david-vscode CLAUDE.md
Instructions for edwardyen724-g/david-vscode, covering claude.md, project: david — agent orchestration for claude code, build, package, install, produce a .vsix and local install.
Warden-AI GEMINI.md
Gemini CLI instructions for rynald0cst0ltziam/Warden-AI, covering warden — context governance and verification layer, session start (important — do this first), layer 1: before starting work — context selection, layer 2: during work — tool output pruning and enforcement hooks (automatic).