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/avikalpa/codex-session-tui/agents-mdgit clone --depth 1 https://github.com/avikalpa/codex-session-tuiWrote 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/avikalpa/codex-session-tui/agents-md)<a href="https://agentmods.dev/instructions/avikalpa/codex-session-tui/agents-md"><img src="https://agentmods.dev/badge/instructions/avikalpa/codex-session-tui/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 | $0.00748 | $0.00748 |
| Opus 5 | $0.00374 | $0.00374 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
codex-session-tui 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 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Purpose
codex-session-explorer is a Rust TUI for inspecting and remapping Codex sessions stored in ~/.codex/sessions.
The key use case is recovering sessions after repository/folder moves by rewriting recorded cwd fields.
Current Scope
- Parse Codex session JSONL files.
- Group sessions by
cwd. - Interactive TUI browsing (projects, sessions, preview).
- Session operations: move, copy, fork across folder contexts.
Architecture
- Runtime: single binary (
src/main.rs) usingratatui+crossterm. - Data source: filesystem scan of
${CODEX_HOME:-~/.codex}/sessions. - Persistence model:
- move: in-place JSONL rewrite + backup
- copy/fork: write new JSONL file under current date path
Safety Rules
- Never mutate a session file without creating a backup first.
- Use atomic writes (
tmp+ rename) for all file writes. - Preserve unknown JSON fields when rewriting; only touch targeted keys (
cwd, and fork metadata keys). - Keep operations local and deterministic; no network side effects.
Developer Workflow
- Run
cargo checkbefore finalizing changes. - Keep UI keybindings visible in the status/footer region.
- Prefer incremental, reviewable changes; avoid broad refactors unless needed for correctness.
- Document any behavior changes in
README.md.
Test-First Protocol
Use a strict test-first loop for all non-trivial changes (especially TUI rendering, scrolling, and session rewrite logic):
- Write a failing test that captures the exact behavior gap before implementing the fix.
- Implement the smallest change necessary to make that test pass.
- Run the narrowest relevant test target first, then full
cargo test. - Refactor only after tests pass, and keep behavior unchanged.
- Add regression tests for any bug fixed from real usage reports.
Coverage expectations:
- Unit tests for pure logic: parsing, filtering, scoring, row mapping, rewrite transforms.
- Integration tests for end-to-end behavior: preview composition, search/filter flows, session operations.
- For TUI bugs, include tests that assert scroll/index mapping and wrapped-line behavior assumptions.
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 · 73 lines · 748 tokens per session scan A 485bf874444e
codex-session-tui AGENTS.md is an instructions file published in the GitHub repository avikalpa/codex-session-tui (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 748 tokens to every session, about $0.0037 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 2026-08-31.
Other instructions, from other repositories
r3bl-open-core GEMINI.md
Instructions for r3bl-org/r3bl-open-core, a project described as: TUI framework and developer productivity apps in Rust 🦀.
terminal-jarvis AGENTS.md
Instructions for BA-CalderonMorales/terminal-jarvis, covering agents.md - terminal jarvis, current shape, key sections, branch strategy and merge-to-develop discipline.
VTCode copilot-instructions.md
Instructions for vinhnx/VTCode, covering vt code agent guidelines, build & test commands, preferred (faster with cargo-nextest), standard cargo commands and fallback (if nextest unavailable).
Monoloth AGENTS.md
Instructions for noahain/Monoloth, covering agents.md, stack, layout, build / test commands and from repo root.
chabeau AGENTS.md
Instructions for permacommons/chabeau, covering general guidelines, additional style note for agents, commit summaries and performance validations.
codexRS AGENTS.md
Instructions for Kiwunaka/codexRS, covering project rules, proportional engineering and universal safety.