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/foundryside-dev/warpline/agents-mdgit clone --depth 1 https://github.com/foundryside-dev/warplineWhat 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 | $0.01006 | $0.01006 |
| Opus 5 | $0.00503 | $0.00503 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade C, and why
warpline AGENTS.md scanned grade C with 1 finding 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 yesterday.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- filigree:instructions:v3.1.0:c1c023c3 --> Copies of this mod
1 near-identical copy found in the catalogue:
- warpline CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Filigree Issue Tracker
filigree tracks this project's work. Use it to find, claim, update and close
issues: filigree session-context at session start, then
filigree start-next-work --assignee <name>.
Full reference: the filigree-workflow skill (patterns, priorities,
observations, error codes), filigree --help, and the mcp__filigree__* tool
schemas. Prefer the MCP tools when available; fall back to the CLI.
Two rules --help will not tell you:
- Claim atomically:
work_start/work_start_next(MCP) orstart-work/start-next-work(CLI). Never chain a claim with a separate status update; that two-step form races other agents. - On
SCHEMA_MISMATCHthe installed filigree is older than the project database. Surface it to the user; do not retry.
Loomweave (code archaeology)
This repo is indexed by Loomweave: it has pre-extracted the tree into a
queryable map of entities (functions, classes, modules, files), the call /
reference / import edges plus relation edges (inherits_from / decorates /
implements / derives), and subsystem clusters. Before grepping the tree to
answer "what calls X", "what subclasses X", "where is X defined", "what
subsystem owns X", or "find the thing that does Y" — ask Loomweave's MCP tools
(mcp__loomweave__*): entity_find, entity_at, entity_callers_list,
entity_relation_list, entity_neighborhood_get, project_status_get.
entity_find is the grep replacement for "find the thing that does Y": it
matches a concept word by substring over name, summary, and docstring content
(e.g. library finds LibraryService), with no embeddings required — reach for
it before grepping. Semantic ranking is the separate, opt-in
entity_semantic_search_list.
Entity IDs are {plugin}:{kind}:{qualified_name}; subsystems are
core:subsystem:{hash}. Never hand-construct one: get it from entity_find /
entity_at, or — for a pasted qualname, Rust :: path, or SEI token — from
entity_resolve, then copy it verbatim into the next tool.
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.
- yesterday First seen · 74 lines · 1,006 tokens per session scan C ad242f6e725e
warpline AGENTS.md is an instructions file published in the GitHub repository foundryside-dev/warpline (0 stars, last pushed 21d ago), licensed MIT. It adds 1,006 tokens to every session, about $0.0050 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.
clawchat-plugin-connect AGENTS.md
Instructions for XMethues/clawchat-plugin-connect, covering agent skills, issue tracker, triage labels and domain docs.
autonomous-dev CLAUDE.md
Claude Code instructions for akaszubski/autonomous-dev, covering autonomous-dev, critical rules, maintainer escape hatches, architecture and code navigation.
icloud-reminders-mcp CLAUDE.md
Claude Code instructions for Lingnik/icloud-reminders-mcp, covering icloud-reminders-mcp — project conventions, backlog: github issues, always, secrets, architecture and testing.