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/asklokesh/loki-mode/claude-mdgit clone --depth 1 https://github.com/asklokesh/loki-modeWrote 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/asklokesh/loki-mode/claude-md)<a href="https://agentmods.dev/instructions/asklokesh/loki-mode/claude-md"><img src="https://agentmods.dev/badge/instructions/asklokesh/loki-mode/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 5.1 | $0.09722 | $0.09722 |
| Opus 5 | $0.04861 | $0.04861 |
| Sonnet 5 | $0.01944 | $0.01944 |
| Haiku 4.5 | $0.00972 | $0.00972 |
Grade F, and why
loki-mode CLAUDE.md scanned grade F with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 700 "$LOKI_RUN_TMP" || { Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://127.0.0.1:57374/api/status | python3 -c "import json,sys; json.load(sys.stdin); print('PASS: API responds')" 2>/dev/null || echo "FAIL: API broken" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf -- "$target" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:57374/ | grep -q "Loki" && echo "PASS: web app serves" || echo "FAIL: web app broken" The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 6d ago First seen · 745 lines · 9,722 tokens per session scan F cedb3c37be9f
loki-mode CLAUDE.md is an instructions file published in the GitHub repository asklokesh/loki-mode (1,054 stars, last pushed 5d ago), with no licence file. It adds 9,722 tokens to every session, about $0.0486 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
yoloai CLAUDE.md
Instructions for kstenerud/yoloai, covering claude code specifics and the quality gate runs itself here.
pxx AGENTS.md
AGENTS.md instructions for cdnwetzel/pxx, covering agents.md — working agreements for ai agents in this repo, what this is, commands, hard rules and conventions.
AutoResearch AGENTS.md
Instructions for Maleick/AutoResearch, covering auto research agent guide, project purpose, source of truth, development rules and security rules.
agentforge CLAUDE.md
Instructions for mrzroot/agentforge, covering claude.md - project directives for claude code, project overview: agentforge, commands & environment, code architecture & philosophy and architectural conventions.
agent-policykit copilot-instructions.md
Instructions for sidrat2612/agent-policykit, covering source of truth, project context, theme governance, engineering governance standard and operating principles.
auto-co-meta CLAUDE.md
Instructions for NikitaDmitrieff/auto-co-meta, covering auto-co -- fully autonomous ai company, mission, operating mode, safety red lines (absolute -- never violate) and team architecture.