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/agentis-tools/ctx/agents-mdgit clone --depth 1 https://github.com/agentis-tools/ctxWhat 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 | $0.00566 | $0.00566 |
| Opus 5 | $0.00283 | $0.00283 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade C, and why
ctx 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 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.
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.
<!-- governance-instructions:v1 --> How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ctx contributor instructions
ctx is the agentis-ctx Rust package and installs the ctx binary. The root
package is not a Cargo workspace; perf/ is an isolated, unpublished harness.
Rust 1.91 is the minimum supported version and the edition is 2021.
Read before changing the repository
governance/agent-workflow.mddefines the contributor workflow.governance/versioning.mdis the canonical SemVer and compatibility policy.governance/guardrails.mddistinguishes automated enforcement from human review.governance/releasing.mdis maintainer-only release procedure.
docs/ is public product documentation and the user manual. Internal policy,
maintainer procedures, CI governance, and agent rules belong in governance/,
never in docs/.
Invariants
- Root
Cargo.toml[package].versionis the only manually edited product version. Usepython3 scripts/version.py; do not hand-edit lockfile versions. - Ordinary PRs do not bump versions. Release preparation must use the tooling, update reviewed changelog notes, and receive the required labels/review.
- Treat CLI flags/defaults, JSON, config, persisted schemas/indexes, Rust API, MCP/plugins, exits, platforms/packaging, and self-update as contracts.
- Add an Unreleased
CHANGELOG.mdentry for product behavior. Never hide a break in prose or update a contract snapshot without reviewing SemVer impact. - Generated harness hooks/plugins/checksums/release notes are not hand-edited.
- Never tag, publish, release, push unrelated changes, weaken gates, or change repository settings without explicit authorization.
Validation
python3 scripts/version.py show
python3 scripts/check-governance.py check
python3 -m unittest discover -s tests/versioning -p 'test_*.py'
cargo fmt --all -- --check
cargo clippy --all-targets --all-features -- -D warnings
cargo test --locked --all-features
cargo test --locked --no-default-features
scripts/ci.sh
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 · 55 lines · 566 tokens per session scan C cec3c97e6ef2
ctx AGENTS.md is an instructions file published in the GitHub repository agentis-tools/ctx (11 stars, last pushed 15d ago), licensed Apache-2.0. It adds 566 tokens to every session, about $0.0028 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 2026-08-30.
Other instructions, from other repositories
har AGENTS.md
Instructions for os-factory/har, covering har — agent development guide, har / agent environment, harnesses in this repo, harness workflow (dogfooding) and run history.
har CLAUDE.md
Instructions for os-factory/har, a project described as: HAR: open agent harness (CLI + MCP) for coding agents. Isolated worktrees, deterministic verify, software factory workflows for Claude Code, Cursor, and Codex.
alego AGENTS.md
Instructions for singula-ai/alego, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.
alego CLAUDE.md
Instructions for singula-ai/alego, a project described as: Build AI Agents like playing LEGOs. Everything is a Plugin.
thinkrail AGENTS.md
Instructions for JetBrains/thinkrail, covering thinkrail, module structure & boundaries (top-priority requirement), engine: pi only, in-process, architecture (three rings) and repo layout.
snip CLAUDE.md
Instructions for edouard-claude/snip, covering claude.md, project overview, key concept, repository structure and architecture.