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/collibra/chip/agents-mdgit clone --depth 1 https://github.com/collibra/chipWhat 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 | $0.01367 | $0.01367 |
| Opus 5 | $0.00683 | $0.00683 |
| Sonnet 5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
chip 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding instructions
- Follow the stepdown rule when determinging the order of functions or other code constructs: we want the code to read like a top-down narrative. Every function to be followed by those at the next level of abstraction so that we can read the program, descending level of abstraction at a time as we read down the list of functions.
- When running a command remember the shell is initialized to the workspace path by default so no need to cd into it.
PR creation instructions
- Keep the commit message short and professional one-liner.
- Use the github CLI to create the PR. The details of the
gh pr createcommand are available below. - To find out what are the changes and generate the PR details, you must compare the current branch with the main branch.
- Any local changes that are not committed to the branch should be ignored.
- Keep the description simple and professional. Do not brag using adjectives like "enhanced" or "comprehensive" or similar.
- You must follow in the following template for the details of the PR. When using the template, you must use github compatible markdown format.
### Description of your changes
<!--
Please include a short summary of the changes and any relevant
motivation and context. List any dependencies that are required
for this change (i.e. Depends on merge of PR in another repo).
-->
---
### Impact Analysis
<!--
Please include any information about analysis that has been
performed with respect to whether or not this change may have
a potentially large or small impact on this or other codebases.
-->
---
#### Checklist
- [x] I have performed a self-review of my code
- [x] My code follows the contribution guidelines of this project
- [x] My changes generate no new warnings
gh pr create --help
Create a pull request on GitHub.
Upon success, the URL of the created pull request will be printed.
When the current branch isn't fully pushed to a git remote, a prompt will ask where
to push the branch and offer an option to fork the base repository. Use `--head` to
explicitly skip any forking or pushing behavior.
`--head` supports `<user>:<branch>` syntax to select a head repo owned by `<user>`.
Using an organization as the `<user>` is currently not supported.
For more information, see <https://github.com/cli/cli/issues/10093>
A prompt will also ask for the title and the body of the pull request. Use `--title` and
`--body` to skip this, or use `--fill` to autofill these values from git commits.
It's important to notice that if the `--title` and/or `--body` are also provided
alongside `--fill`, the values specified by `--title` and/or `--body` will
take precedence and overwrite any autofilled content.
The base branch for the created PR can be specified using the `--base` flag. If not provided,
the value of `gh-merge-base` git branch config will be used. If not configured, the repository's
default branch will be used. Run `git config branch.{current}.gh-merge-base {base}` to configure
the current branch to use the specified merge base.
Link an issue to the pull request by referencing the issue in the body of the pull
request. If the body text mentions `Fixes #123` or `Closes #123`, the referenced issue
will automatically get closed when the pull request gets merged.
By default, users with write access to the base repository can push new commits to the
head branch of the pull request. Disable this with `--no-maintainer-edit`.
Adding a pull request to projects requires authorization with the `project` scope.
To authorize, run `gh auth refresh -s project`.
USAGE
gh pr create [flags]
ALIASES
gh pr new
FLAGS
-a, --assignee login Assign people by their login. Use "@me" to self-assign.
-B, --base branch The branch into which you want your code merged
-b, --body string Body for the pull request
-F, --body-file file Read body text from file (use "-" to read from standard input)
-d, --draft Mark pull request as a draft
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 · 121 lines · 1,367 tokens per session scan A d82fba3e2fa2
chip AGENTS.md is an instructions file published in the GitHub repository collibra/chip (36 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,367 tokens to every session, about $0.0068 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.