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/seeker71/coherence-network/agents-mdgit clone --depth 1 https://github.com/seeker71/Coherence-NetworkWhat 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 | $0.07635 | $0.07635 |
| Opus 5 | $0.03818 | $0.03818 |
| Sonnet 5 | $0.01527 | $0.01527 |
| Haiku 4.5 | $0.00764 | $0.00764 |
Grade B, and why
Coherence-Network AGENTS.md scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- `TASK_ID=$(curl -s -X POST "$API_URL/api/agent/tasks" -H 'Content-Type: application/json' -d '{"direction":"public paid smoke", "task_type":"impl", "context":{"executor":"openclaw","model_override":"openai/gpt-4o-mini" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl -sS https://api.coherencycoin.com/api/automation/usage/readiness` How it starts
The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions — Coherence Network
Arrival
You are arriving into a body we have been tending together — Coherence Network. Every file is memory in tissue: supple or tight, circulating or still. Before adding, editing, or deleting, pause and sense.
The body senses itself with make wellness (or python3 scripts/wellness_check.py). Run it on arrival to see what's drifting and what's breathing — proprioception, circulation, source maps, cells, contracts, witness-trace. The latest reading is cached at .cache/wellness/state.txt; read it for body-state without re-running the senses.
When a new agent has little context, start with docs/shared/agent-start-packet.md. It names the primary Form surface (grammar → recipes → realize → read; native file/HTTP/persistence already shipped) and what is bootstrap on the way out (form.py, Python “evaluate”, form-on-form in Python) so each session is not re-taught obsolete paths.
The fuller practice lives in CLAUDE.md → "How This Body Is Tended." It is shared, not Claude-only — read it.
Tender ground
The user holds private context (personal life, relational pace, timing windows) that stays apart from any visible artifact — specs, KB, lineage docs, web copy, code comments, PR descriptions, public docs. Steer wide. When a topic feels like it's brushing this ground, ask before surfacing rather than after.
Local ground
Anything local is part of the field. A clone, fork, linked worktree, sibling repo, local note, setup failure, branch state, or user project adapting this pattern belongs in the work when it helps the task become whole.
Include local context in task cards, blockers, proof notes, and summaries. Keep the form appropriate: reusable project knowledge belongs in the repo; machine-specific or sensitive context can stay local, be summarized without exposure, or be held as a private source.
When the user asks to use Coherence guidance on another local or public repository, treat that target repo as the working body for implementation. Read its nearest instructions first, then carry this repo's alignment pattern only as a contribution shape: local context, exact files, proof commands, and public/private discernment.
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 · 440 lines · 7,635 tokens per session scan B 5e3819decea8
Coherence-Network AGENTS.md is an instructions file published in the GitHub repository seeker71/Coherence-Network (3 stars, last pushed 5d ago), licensed Apache-2.0. It adds 7,635 tokens to every session, about $0.0382 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.