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/coeusyk/inference-x/claude-mdgit clone --depth 1 https://github.com/coeusyk/inference-xWrote 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/coeusyk/inference-x/claude-md)<a href="https://agentmods.dev/instructions/coeusyk/inference-x/claude-md"><img src="https://agentmods.dev/badge/instructions/coeusyk/inference-x/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 | $0.00615 | $0.00615 |
| Opus 5 | $0.00308 | $0.00308 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
inference-x 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 4d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — InferenceX
Repo-local agent instructions for Claude Code / Cursor. Canonical OpenSpec and
architecture rules live in AGENTS.md. Read AGENTS.md first
and follow it for file boundaries, Engine Boundary (DEC-047), OpenSpec order,
and anti-scope.
Tooling (mandatory every session)
Token efficiency is standing policy. Full rationale and command tables:
AGENTS.md → Agent tooling.
Two paths only — no third
| Default | Escapes only when |
|---|---|
context-mode — ctx_batch_execute / ctx_execute / ctx_execute_file / ctx_search / ctx_fetch_and_index / ctx_index |
— |
rtk proxy <cmd> |
Host mutation that must persist: git, openspec archive, real-FS moves, host exit-code-critical runs |
Never use bare Bash/Shell for gates or inspection. Never use bare rtk <cmd>
when the operation must persist — use rtk proxy. Prefer wrapping pytest/ruff/mypy/uv
with rtk … inside context-mode so stdout stays compact.
token-savior MCP (if present)
If token-savior appears in the session MCP catalog, prefer its tools over
grep-then-read for navigation and impact (find_symbol, get_full_context,
search_codebase, get_call_chain, get_change_impact, get_edit_context, …).
If it is absent, fall back to context-mode — do not invent tool calls.
Why
- RTK — cuts most bash-output bytes (often 60–90%; git frequently higher).
- context-mode — keeps raw tool output out of the chat (~98% reduction path); retrieve with search.
- token-savior — indexed symbols/deps instead of loading whole files.
Branches and commits
See AGENTS.md → Branches, commits, and GitHub rulesets.
Summary:
- Branch from
develop:feat/…,fix/…,chore/…,docs/… - PR into
develop(release promotion →mainseparately) - Never force-push
main/develop; never delete them - Required CI job name:
checks(blocks merge on red) - Ruleset Protect Main requires PRs + code-owner review on
main - Commit only when the user asks; one concern per PR
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.
- 4d ago First seen · 55 lines · 615 tokens per session scan A 09edeb32f2ef
inference-x CLAUDE.md is an instructions file published in the GitHub repository coeusyk/inference-x (2 stars, last pushed 24d ago), licensed MIT. It adds 615 tokens to every session, about $0.0031 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
bridgenode-skill AGENTS.md
AGENTS.md instructions for bridgenode-ai/bridgenode-skill, covering agents.md — bridgenode skill & examples, what bridgenode is, how an agent pays (x402 flow, 4 steps), quick start (buyer side) and curl — full flow in examples/.
Mooncake AGENTS.md
AGENTS.md instructions for kvcache-ai/Mooncake, covering agents.md, docs/ directory changes and pull request guidelines.
commonly CLAUDE.md
Claude Code instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.
ocp CLAUDE.md
Claude Code instructions for dtzp555-max/ocp, covering ocp project session instructions, before starting any task, classify the change first: class a or class b, hard requirements for server.mjs changes and iron rules in force.
fastagent AGENTS.md
AGENTS.md instructions for fastagent-sh/fastagent, covering fastagent — agent guide, what this is, source of truth, repo map and devx principle stack.
langfuse AGENTS.md
AGENTS.md instructions for langfuse/langfuse, a project described as: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23.