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/ahundt/ai-session-search/agents-mdgit clone --depth 1 https://github.com/ahundt/ai-session-searchWrote 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/ahundt/ai-session-search/agents-md)<a href="https://agentmods.dev/instructions/ahundt/ai-session-search/agents-md"><img src="https://agentmods.dev/badge/instructions/ahundt/ai-session-search/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 5.1 | $0.01338 | $0.01338 |
| Opus 5 | $0.00669 | $0.00669 |
| Sonnet 5 | $0.00268 | $0.00268 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
ai-session-search 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 6d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Session Search agent guidance
Read by every tool following the AGENTS.md convention. CLAUDE.md imports it,
so change it here only.
Rust first: logic, checks, and tooling belong in the crate, and Python carries only the binding surface and the tests that must exercise it.
Setup
Rust 1.88 or newer, CPython 3.12 through 3.14 with the standard GIL (3.12 is the floor; 3.12–3.14 are what CI tests), and uv.
uv sync --locked --all-extras
uv run maturin develop --uv # abi3 extension into the venv; pytest fails without it
Build
./run_ci_local.sh # host-platform gate, before proposing a commit
cargo test -p ai-session-search <test name> # focused Rust
uv run pytest tests/<file>.py -k <test name> # focused Python
cargo clippy --workspace --all-targets --all-features --locked -- -D warnings
uv run ruff check . && uv run mypy ai_session_search tests
The gate reproduces the required Rust, Python, license, and workflow-security commands that use the
current host and toolchain. The required CI matrix still owns the MSRV build, macOS/Windows/Linux and
CPython 3.12–3.14 coverage, and registry, path, and Git install pathways. That matrix has caught what
a green local gate could not: a test building a file:// URL by string interpolation passed where
paths start with a separator and failed on Windows, where the drive letter parses as the URL host.
Keep this command map accurate when a required job changes. A missing local command makes a green
run mean less than it reads as: cargo doc was absent once, and a public item linking a private one
passed locally before failing the hosted rust job. Tools the gate does not install — actionlint,
cargo-deny — report named skips and exact pinned install commands; when installed, their versions
must match the workflow pins before their results count as hosted-command evidence.
Run the gate with no environment prefix. Never prefix
AI_SESSION_SEARCH_RUSTC_WRAPPER=: it exports an empty RUSTC_WRAPPER and
disables sccache. Use it only when an inherited wrapper is broken. Before step one
the gate prints the wrapper it resolved and whether incremental compilation is on;
read that line before concluding a build is slow for another reason.
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.
- 6d ago First seen · 114 lines · 1,338 tokens per session scan A ee98f44f263e
ai-session-search AGENTS.md is an instructions file published in the GitHub repository ahundt/ai-session-search (37 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,338 tokens to every session, about $0.0067 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
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
vibetags com-example-config-AsyncTestConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
McpServer AGENTS.md
AGENTS.md instructions for sharpninja/McpServer, covering agent instructions, session start, rules, byrd test gate and where things live.