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/cyrax321/continuum/agents-mdgit clone --depth 1 https://github.com/Cyrax321/CONTINUUMWhat 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 | $0.00555 | $0.00555 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
CONTINUUM 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (and their operators) working in this repository.
Before you touch anything
- Run
git statusandgit log --oneline -10to confirm current state. Don't trust a prior summary, including your own from an earlier session. - Confirm you're operating on the canonical copy of this repo (check
git remote -vand that you're== origin/mainbefore assuming clean). - Read STATUS.md and CHANGELOG.md's
[Unreleased]section for current, accurate context before making claims about what is or isn't done.
Commit and push conventions
- No em dashes (—) anywhere in commit messages, code comments, or docs. Use commas, periods, or parentheses instead.
- No AI attribution or fingerprints: no "Generated with [tool]", no AI co-author trailers, no comments naming an AI agent or tool. Commits and code should read as if written by the project maintainer.
- Never force-push (to any branch, including with
--force-with-lease, including to amend your own just-pushed commit) without explicit confirmation from the maintainer first. If you believe a force-push is needed, stop and explain why instead of doing it. - Prefer small, focused commits over large multi-purpose ones.
Issues and pull requests
- Before opening an issue or PR, check
.github/ISSUE_TEMPLATE/and.github/PULL_REQUEST_TEMPLATE.md(or equivalent) for this repo's actual templates, and follow them exactly. Do not invent a new format or structure, use the existing template's headings and fields as-is. - If no template exists for the type of issue/PR you're creating, say so explicitly rather than improvising one that looks official.
Verification standard
- Don't report something as fixed, verified, or passing unless you have direct evidence (raw command output, not a paraphrase) from this session.
- If a diagnosis is plausible but unverified, say so explicitly rather than presenting it as confirmed. A confident wrong answer is worse than an honest "I'm not sure."
- When claiming a bug is fixed, include a regression test that would have caught it, and show it failing on the old code path if practical.
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 · 52 lines · 555 tokens per session scan A bea6144de2d9
CONTINUUM AGENTS.md is an instructions file published in the GitHub repository Cyrax321/CONTINUUM (28 stars, last pushed 2d ago), licensed Apache-2.0. It adds 555 tokens to every session, about $0.0028 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
Jixu AGENTS.md
Instructions for joe960913/Jixu, covering jixu repository instructions, 1. read order, 2. sources of truth, 3. canonical concepts and 4. architecture invariants.
golem AGENTS.md
AGENTS.md instructions for golemcloud/golem, covering golem development guide, backward compatibility, prerequisites, building and makefile.toml script conventions.
Jixu CLAUDE.md
Instructions for joe960913/Jixu, a project described as: Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.
workflow AGENTS.md
AGENTS.md instructions for vercel/workflow, covering agent instructions, architecture, core components, workflow execution model and development commands.
waku-agent CLAUDE.md
Instructions for ShenSeanChen/waku-agent, covering waku-agent — working conventions, architecture map (file ↔ diagram box), rules and commands.
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.