Borrowing it
Nothing to install: this file belongs to nishantdesai/codex-history. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nishantdesai/codex-history/main/AGENTS.mdgit clone --depth 1 https://github.com/nishantdesai/codex-historyWrote 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/nishantdesai/codex-history/agents-md)<a href="https://agentmods.dev/instructions/nishantdesai/codex-history/agents-md"><img src="https://agentmods.dev/badge/instructions/nishantdesai/codex-history/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/nishantdesai/codex-history/agents-md"><img src="https://agentmods.dev/badge/instructions/nishantdesai/codex-history/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00500 | $0.00500 |
| Opus 5.5 | $0.00200 | $0.00200 |
| Sonnet 5.5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
codex-history 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 2mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose
This repository builds codex-history, a Rust CLI for querying locally accessible Codex session history.
Source of truth
When making architectural or scope decisions, follow:
docs/SPEC.mdREADME.mddocs/RELEASING.md
If these documents conflict, prefer the more conservative interpretation and do not widen scope.
Core implementation decision
Use direct local Codex history/session-log parsing as the primary source of truth.
Do not implement the App Server adapter in the initial build. Keep the code structure compatible with a later adapter, but defer that work until after the local-first tool is working.
Working rules
- Keep the tool read-only
- Do not add any feature that mutates Codex history
- Do not depend on undocumented private endpoints
- Prefer local backend first and primary
- Keep App Server integration deferred until later
- Keep the index opt-in
- Use synthetic fixtures only
- Do not check in real history data, indexes, or machine-specific paths
Code quality rules
- prefer small, reviewable commits
- add tests for each feature
- keep modules narrowly scoped
- use explicit errors and typed results
- avoid introducing async complexity unless clearly necessary
- preserve unknown item/event variants instead of discarding them
Output and UX rules
- stdout for successful command output
- stderr for diagnostics and errors
- never mix prose into
--jsonoutput - make
--helptext concise and accurate - keep
--jsonand--ndjsonas the machine-facing interfaces for search/grep - keep human-readable
search/grepoutput aligned with the implemented modes: default output is grouped by thread with per-hit full text blocks, and--compactis a markdown-table-style one-line view that should not deliberately truncate thread name, cwd, or preview text
Packaging rules
- binary name must remain
codex-history - repository license is MIT unless the user explicitly changes it
- release artifacts must be compatible with the Homebrew tap at
github.com/nishantdesai/homebrew-tap
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.
- 2mo ago First seen · 66 lines · 500 tokens per session scan A e89ebda7718e
codex-history AGENTS.md is an instructions file published in the GitHub repository nishantdesai/codex-history (10 stars, last pushed 7mo ago), licensed MIT. It adds 500 tokens to every session, about $0.0020 per session on Opus 5.5. 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.
codex-history AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-history AGENTS.mdnishantdesai/codex-history | Instructions file | 10 | 7mo ago | MIT | A | 500 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |