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/sysevol-ai/codenib/agents-mdgit clone --depth 1 https://github.com/sysevol-ai/CodeNibWrote 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/sysevol-ai/codenib/agents-md)<a href="https://agentmods.dev/instructions/sysevol-ai/codenib/agents-md"><img src="https://agentmods.dev/badge/instructions/sysevol-ai/codenib/agents-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 | $0.02451 | $0.02451 |
| Opus 5 | $0.01226 | $0.01226 |
| Sonnet 5 | $0.00490 | $0.00490 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
CodeNib 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 today.
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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
CodeNib is a Python 3.10+ code analysis agent with tree-sitter chunking, semantic graph construction, hybrid retrieval, and MCP-facing search tools. Use this file as the repo-level contract for Codex and other code agents.
Layered Objectives
Work in this order unless the user gives a narrower task:
- Protect
main: do not merge draft PRs, PRs with unresolved code failures, or stacked PRs whose dependency chain is not clear. - Make changes reviewable: keep commits focused, preserve existing ownership boundaries, and avoid unrelated refactors.
- Verify the changed surface: run the smallest relevant test first, then widen to the job or marker tier that matches the risk.
- Keep stacked work coherent: merge or rebase dependencies before dependents, and re-check diffs after a base branch changes.
- Codify repeated feedback here or in the nearest directory-specific rules file so future agents do not repeat the same mistake.
For broad multi-step work, keep an explicit layered goal active until the requested surface is implemented, locally verified, documented, and reconciled with relevant PRs/issues. Do not mark a broad goal complete just because a single subgoal landed. Prefer local targeted verification and continued implementation over waiting on slow remote CI; run the remote/slow tier after the merge queue or feature batch is otherwise coherent.
For the current multi-language SCIP cold-start and acceleration program, use
docs/scip_multilanguage_roadmap.md as the durable objective record. Update it
whenever a backend is promoted, a C++ acceleration gate changes, or a related
issue/PR is closed.
For storage scope and subtraction, use docs/storage_backend_roadmap.md as the
durable objective record. Update it whenever the Wiki database boundary
changes, a retained compatibility surface is removed, or a proposal attempts
to reopen the generic backend program.
For the cognitive-debt reduction program, use
docs/cognitive_debt_roadmap.md as the durable objective record. Update it
whenever a package changes lifecycle class, an experimental surface is retired,
an architectural dependency direction changes, or a subtraction iteration is
completed.
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.
- today Changed · +38 lines · +531 tokens per session f9452e59e4b1
- 4d ago First seen · 155 lines · 1,920 tokens per session scan A 13f9666a9c1f
CodeNib AGENTS.md is an instructions file published in the GitHub repository sysevol-ai/CodeNib (85 stars, last pushed today), licensed Apache-2.0. It adds 2,451 tokens to every session, about $0.0123 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
code-meridian AGENTS.md
Instructions for Driftya/code-meridian, covering agents.md, behavior expectations, required codemeridian usage, trigger rules and repository rules.
code-meridian copilot-instructions.md
Instructions for Driftya/code-meridian: Read AGENTS.md — it is the single source of truth for architecture, conventions, tool usage triggers, and contribution rules for this repository.
code-meridian CLAUDE.md
Instructions for Driftya/code-meridian: Read AGENTS.md — it is the single source of truth for architecture, conventions, tool usage triggers, and contribution rules for this repository.
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
repobrain AGENTS.md
AGENTS.md instructions for study8677/repobrain: Beautiful is better than ugly. Explicit is better than implicit. Simple is better than complex. Complex is better than complicated. Flat is better than nested. Sparse is better than dense. Readability counts. Special cases aren't special enough to break the rules.…
sverklo CLAUDE.md
Instructions for sverklo/sverklo, covering sverklo development, using sverklo tools, project structure and build & test.