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/danielcardonarojas/codemark/gemini-mdgit clone --depth 1 https://github.com/DanielCardonaRojas/codemarkWrote 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/danielcardonarojas/codemark/gemini-md)<a href="https://agentmods.dev/instructions/danielcardonarojas/codemark/gemini-md"><img src="https://agentmods.dev/badge/instructions/danielcardonarojas/codemark/gemini-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 | $0.00345 | $0.00345 |
| Opus 5 | $0.00172 | $0.00172 |
| Sonnet 5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
codemark GEMINI.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 3d 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.
What it actually says
Development Workflow
- Always run the linter and formatter before creating any PRs.
Debugging with the TUI logging system
The TUI writes structured logs to $TMPDIR/codemark-tui.log using tracing. Control verbosity via RUST_LOG:
RUST_LOG=codemark=debug cargo run -p codemark-tui # all subsystems at debug
RUST_LOG=codemark::git=trace # only git at trace
RUST_LOG=codemark::db=debug,codemark::http=debug # multiple subsystems
Available subsystem targets:
| Target | Covers |
|---|---|
codemark::git |
rev-parse, ls-tree, status, context/metadata detection |
codemark::db |
DB open, migrations, bookmark/collection/resolution CRUD |
codemark::http |
HTTP client, remote tour listing, pack download/upload, sync |
codemark::shell |
External editor spawning (program, args, errors) |
codemark::auth |
Server authorization decisions: repo read/write access checks, public-repo visibility, allow/deny outcomes |
codemark::embeddings |
Embedding provider lifecycle: shared-provider cache reuse vs. creation, model loading |
When adding new functionality, instrument it with tracing::debug! (or info!/warn!/error! as appropriate) using the matching subsystem target. If adding a new subsystem, define a new codemark:: target and add a row to the table above.
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.
- 3d ago First seen · 29 lines · 345 tokens per session scan A 0ac441ab8399
codemark GEMINI.md is an instructions file published in the GitHub repository DanielCardonaRojas/codemark (123 stars, last pushed 14d ago), licensed MIT. It adds 345 tokens to every session, about $0.0017 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
looper_rust AGENTS.md
Instructions for quangdang46/looper_rust, covering looper rust — ai agent guidelines, build, test, lint and workspace members.
rag-ferrite AGENTS.md
AGENTS.md instructions for lelabdev/rag-ferrite, covering rag-ferrite — moteur rag personnel (rust), stack, architecture, décisions d'architecture and structure du code.
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.