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/morluto/flameox/agents-mdgit clone --depth 1 https://github.com/morluto/flameoxWhat 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 | $0.01170 | $0.01170 |
| Opus 5 | $0.00585 | $0.00585 |
| Sonnet 5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
flameox 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Product Direction
flameox is a permanently local evidence layer for coding agents investigating performance, memory, execution, concurrency, and reliability. It gives an agent a reproducible path from a runtime symptom to a conclusion that another person or agent can inspect and try to disprove.
Existing profilers, benchmark tools, debuggers, and trace processors measure runtime behavior. flameox coordinates those tools, preserves their native artifacts and provenance, extracts bounded evidence, and compares runs and experiments. The agent forms hypotheses, chooses discriminating experiments, and explains the conclusion.
A typical investigation moves through:
symptom → capture or import → bounded evidence → hypothesis
→ discriminating experiment → supported, refuted, or inconclusive finding
flameox is not a profiler, a generic bug finder, a hosted observability service,
an unrestricted command or SQL gateway, or an arbitrary source-code modification
system. Agents may create and update flameox.toml through the structured
workload configuration tool.
A feature belongs when it improves trustworthy collection, evidence
preservation, cross-run analysis, experimental validity, or bounded agent
drill-down without replacing an upstream tool.
When changing the product:
- preserve native artifacts, provenance, failed attempts, and experimental structure;
- distinguish observed, derived, and inferred claims;
- prefer bounded task-shaped operations over arbitrary commands or SQL;
- prefer integrating maintained measurement and replay tools through typed adapters; build custom measurement or replay machinery only when maintained tools cannot satisfy the required evidence, safety, or reproducibility contract;
- keep the SQLite control plane authoritative for mutable intent and lifecycle, immutable artifacts and Parquet authoritative for preserved evidence, and DuckDB rebuildable;
- keep CLI and MCP as thin transports over the same application services;
- let agents configure validated named workloads and proceed directly to planning;
- expose coverage, limitations, compatibility, and containment truthfully;
- optimize for investigation leverage, not integration count.
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 · 124 lines · 1,170 tokens per session scan A 3422ea77954f
flameox AGENTS.md is an instructions file published in the GitHub repository morluto/flameox (49 stars, last pushed 2d ago), licensed MIT. It adds 1,170 tokens to every session, about $0.0059 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
open-design AGENTS.md
AGENTS.md instructions for nexu-io/open-design, covering directory guide, core documentation index, workspace directories, inactive or placeholder directories and development workflow.
ORG2 AGENTS.md
AGENTS.md instructions for org2AI/ORG2, covering agents.md — agent skill routing for orgii, skill routing table, root-cause-first bug fixing, default delivery flow and ui copy conventions.
open-design CLAUDE.md
Claude Code instructions for nexu-io/open-design, a project described as: 🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files…
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.
dreamd AGENTS.md
Instructions for botzrDev/dreamd, covering agents.md — dreamd, what this repo builds, repository layout, build and test and architectural conventions — read before making changes.
RepoRelay AGENTS.md
Instructions for Lukie-81/RepoRelay, covering reporelay contributor instructions and reporelay handoff.