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/jrm-fusional/fusional/claude-mdgit clone --depth 1 https://github.com/JRM-FusionAL/FusionALWrote 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/jrm-fusional/fusional/claude-md)<a href="https://agentmods.dev/instructions/jrm-fusional/fusional/claude-md"><img src="https://agentmods.dev/badge/instructions/jrm-fusional/fusional/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 | $0.03684 | $0.03684 |
| Opus 5 | $0.01842 | $0.01842 |
| Sonnet 5 | $0.00737 | $0.00737 |
| Haiku 4.5 | $0.00368 | $0.00368 |
Grade A, and why
FusionAL CLAUDE.md scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Verify: `curl http://localhost:8009/health` Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Use `# nosec B404` on subprocess imports, `# nosec B603` on list-form subprocess.run. How it starts
The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — FusionAL
SESSION INIT — RUN THIS FIRST
Before responding to anything, in this order:
- Read
C:\Users\puddi\Projects\fusional-knowledge-base\00-CURRENT-STATUS\STATUS.md - Read
C:\Users\puddi\Projects\fusional-knowledge-base\00-CURRENT-STATUS\PRIORITIES.md - Read
C:\Users\puddi\Projects\fusional-knowledge-base\05-RECALL\SOLVED-ISSUES.md - State runtime: "Running as: on , tools available: "
RECALL PROTOCOL (mandatory, visible)
Before debugging ANY error or unexpected behavior:
- State "Recall check: searching SOLVED-ISSUES for "
- State outcome: "Match: SI-XXX — applying documented fix" OR "No match — proceeding with new diagnosis"
The Recall check is VISIBLE OUTPUT. If the line is not in the response, the check did not happen.
AUTO-LOG PROTOCOL (mandatory, ambient)
While working, monitor for AUTO-LOG TRIGGERS: wrong assumption corrected, path/config drift, command failed + root cause identified, protocol violation, cross-system surprise, "why isn't this working" >2 min, repeated pattern.
When a trigger fires:
- State: "Auto-log trigger: — drafting SI-XXX"
- Read
C:\Users\puddi\Projects\fusional-knowledge-base\05-RECALL\SOLVED-ISSUES.md, find highest SI number - Append entry IMMEDIATELY before "## TEMPLATE — copy this for new entries"
- Confirm: "Logged SI-XXX: "
- Continue the original task
Format: ## SI-XXX: <title> + **Symptoms:** + **Root cause:** + **Fix:** + **Verified:** YYYY-MM | **Source:** <ctx> + **Tags:**
Do NOT ask permission. Do NOT batch logs. Do NOT skip when uncertain.
CRITICAL FAILURE MODES (already logged — do not repeat)
SI-001 through SI-011 in SOLVED-ISSUES.md cover Claude Desktop timeouts, Tailscale config, Docker paths, secrets, hardware diagnosis, PowerShell SSH, runtime assumptions, silent recall skips, handoff conflation, path drift, and force-push divergence.
REPO-SPECIFIC CONTENT BELOW
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.
- 5d ago First seen · 411 lines · 3,684 tokens per session scan A 280d6f7ae6c6
FusionAL CLAUDE.md is an instructions file published in the GitHub repository JRM-FusionAL/FusionAL (1 stars, last pushed today), licensed MIT. It adds 3,684 tokens to every session, about $0.0184 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
cloakbrowser-mcp AGENTS.md
AGENTS.md instructions for swimmwatch/cloakbrowser-mcp, covering agents.md, about the project, golden rules, project layout and daily commands.
KACHOW-Teknofest-2026 AGENTS.md
Instructions for chyp3r/KACHOW-Teknofest-2026, covering agents.md, amaç, repository yapısı, backend/ and frontend/.
markitdown-mcp AGENTS.md
Instructions for trsdn/markitdown-mcp, covering ai agents integration guide, 🤖 quick reference for ai agents, primary use cases, available tools and 🛠️ tool usage guide.
cloakbrowser-mcp copilot-instructions.md
Copilot instructions for swimmwatch/cloakbrowser-mcp: Follow AGENTS.md for project-wide coding, testing, documentation, changelog, and commit rules.
GuideAnts copilot-instructions.md
Copilot instructions for Elumenotion/GuideAnts, a project described as: AI work that doesn't evaporate. A workspace for building, tuning, and publishing governed AI products.
che-word-mcp CLAUDE.md
Claude Code instructions for PsychQuant/che-word-mcp, covering che-word-mcp 開發指引, 專案結構, 重要路徑規則, binary 安裝位置 and mcpb 打包檔位置.