Borrowing it
Nothing to install: this file belongs to dPeluChe/trs. 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/dPeluChe/trs/main/AGENTS.mdgit clone --depth 1 https://github.com/dPeluChe/trsWrote 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/dpeluche/trs/agents-md)<a href="https://agentmods.dev/instructions/dpeluche/trs/agents-md"><img src="https://agentmods.dev/badge/instructions/dpeluche/trs/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/dpeluche/trs/agents-md"><img src="https://agentmods.dev/badge/instructions/dpeluche/trs/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 | $0.01587 | $0.01587 |
| Opus 5.5 | $0.00635 | $0.00635 |
| Sonnet 5.5 | $0.00317 | $0.00317 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade B, and why
trs AGENTS.md scanned grade B with 2 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 1mo 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
anti-preamble / anti-narration / structured-output directives. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `trs upgrade`: detects the install channel (npm / curl) and re-runs How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: trs (Token-Reducing Shell)
What is trs
A Rust CLI that transforms noisy terminal output into compact, structured signal. Cuts ~70% of the tokens AI agents spend on terminal output, measured on real sessions (see docs/development/benchmarks/).
Pre-generated codebase digest
docs/development/codebase-digest.md
is a snapshot of the entire trs codebase produced by trs ingest.
Drop it into any agent's context for an instant map of the project
without having to run trs ingest yourself.
The digest can drift from HEAD between releases. Regenerate before
tagging a release, or whenever src/ has moved meaningfully.
Run ./scripts/sync-codebase-digest.sh. It uses trs from PATH and
falls back to ./target/release/trs if one isn't installed.
Related commands worth knowing
trs stats: cumulative savings across commands (shows date range, today vs. average, last command, top-reducers).trs doctor: installation health check. Warns when AGENTS.md / CLAUDE.md exceed ~5k tokens and points attrs audit-docs.trs audit-docs: static analysis of agent instruction files (CLAUDE.md, AGENTS.md, rules files). Surfaces cross-file duplicates, embedded code/SQL/JSON blocks that belong elsewhere, dead@imports, and (for code fences) cross-references declared symbols against the actual source tree (so you can REMOVE ones already defined in src/ and EXTRACT ones that don't live anywhere yet).trs output-saver: install a short output-reduction rules block into each agent's global config (AGENTS.md / CLAUDE.md / Cursor rules). Closes the symmetric gap: trs compresses what agents SEE viatrs rewrite; output-saver compresses what they EMIT via anti-preamble / anti-narration / structured-output directives. Check-first by default (--installto commit,--removeto undo).trs ingest: project digest for LLM consumption. Use symbol index, compression levels, orowner/repoURL shorthand.trs init --show: see which AI agents have trs hooks installed.trs upgrade: detects the install channel (npm / curl) and re-runs it for the latest release.--checkdry-runs,-yskips the confirmation prompt. Seedocs/features/upgrade.md.trs init <tool>: now runs a collision pre-check: detects hooks from other token-compression tools (via@importstoo) and aborts by default.--replaceremoves competitor hooks cleanly,--forceinstalls alongside (risky, double-compression can corrupt output). Seedocs/support/other-token-savers.mdfor the list of tools we coexist with.trs stats --by-agent: breakdown by which AI agent fired each rewrite. Reads theTRS_AGENTenv var thattrs rewriteand plugin templates inject into the command line. Rules-only agents and direct shell runs show as(untagged).- TRS_SKIP=1 prefix: per-invocation bypass. Agents (or users)
that need raw output for a specific command can prefix
TRS_SKIP=1 <cmd>;trs rewritepasses it through unchanged.
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.
- 1mo ago Changed · +14 tokens per session 6221f5fb7191
- 1mo ago First seen · 118 lines · 1,573 tokens per session scan B 277d6be4ba51
trs AGENTS.md is an instructions file published in the GitHub repository dPeluChe/trs (14 stars, last pushed 7d ago), licensed MIT. It adds 1,587 tokens to every session, about $0.0063 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks the agent to reveal its instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.