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/dosu-ai/decant/agents-mdgit clone --depth 1 https://github.com/dosu-ai/decantWrote 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/dosu-ai/decant/agents-md)<a href="https://agentmods.dev/instructions/dosu-ai/decant/agents-md"><img src="https://agentmods.dev/badge/instructions/dosu-ai/decant/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 | $0.01512 | $0.01512 |
| Opus 5 | $0.00756 | $0.00756 |
| Sonnet 5 | $0.00302 | $0.00302 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
decant 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents and contributors working in this repository. Keep
changes small, tested, and consistent with the patterns already present.
CLAUDE.md is a symlink to this file so project guidance has one source of
truth.
Project overview
Decant is a local-first Bun and TypeScript application that turns Claude Code
and Codex JSONL session logs into a normalized, full-text-searchable SQLite
archive. The decant CLI owns parsing, ingest, reads, reports, distillation,
recommendations, watch mode, and the React UI served by decant serve.
Start with these files and guides:
src/cli.tshandles command composition, output, and exit-code policy.src/sources/contains source parsers and the primary extension point.src/db.ts,src/schema.sql, andsrc/schema-manifest.tsmanage storage and schema.src/server.tsandsrc/ui/serve the local API and web UI.docs/architecture.mdmaps module boundaries and data flow.docs/analytics-methodology.mddetails metric definitions.docs/data-lifecycle.mddescribes sync and local state.docs/api/openapi.yamldefines the local API contract.docs/distribution.mdcovers npm, installer, Homebrew, Docker, and source builds.docs/adding-a-source.mdprovides the parser contribution checklist.
Setup and commands
Run commands from the repository root. Bun 1.3 or newer is required. Docker is only needed when validating the container image.
bun run devperforms a frozen dependency install, startup sync, local UI, and source watcher.bun run src/cli.ts --helpruns the CLI from source.bun testruns the test suite.bunx tsc --noEmitruns the type check.bunx biome check .runs the formatting and lint check.just checkruns the full local gate, including the native distribution staging smoke. It needs network access because the smoke packs and installs the npm launcher packages.
The default archive is ~/.decant/decant.db. Override it with DECANT_DB or
--db. Set DECANT_NO_SYNC or pass --no-sync whenever a command points at a
scratch archive, or automatic sync may populate it from the real Claude Code
and Codex directories.
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 · 139 lines · 1,512 tokens per session scan A 6a1ef32cedbc
decant AGENTS.md is an instructions file published in the GitHub repository dosu-ai/decant (59 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,512 tokens to every session, about $0.0076 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
agenttrail AGENTS.md
Instructions for sodiumsun/agenttrail: Maintain PLAN.md as the living plan. It is read by the project OWNER, not by you — write it for them.
agenttrail CLAUDE.md
Instructions for sodiumsun/agenttrail: Maintain PLAN.md as the living plan. It is read by the project OWNER, not by you — write it for them.
helmor AGENTS.md
Instructions for dohooo/helmor, covering agents.md, what is helmor, commands, architecture and three-process model.
matt-skills-with-to-goal CLAUDE.md
Instructions for tt-a1i/matt-skills-with-to-goal: Skills are organized into bucket folders under skills/.
ephemeral-sandbox CLAUDE.md
Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.
code-context AGENTS.md
Instructions for infino-ai/code-context, covering code-context: notes for ai agents, project overview, repo map, build, test, gates and conventions.