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/fullstack-build/tslog/agents-mdgit clone --depth 1 https://github.com/fullstack-build/tslogWhat 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 | $0.03386 | $0.03386 |
| Opus 5 | $0.01693 | $0.01693 |
| Sonnet 5 | $0.00677 | $0.00677 |
| Haiku 4.5 | $0.00339 | $0.00339 |
Grade A, and why
tslog 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 yesterday.
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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview
tslog is a TypeScript logger for browsers, Node.js, Deno, and Bun, React Native, and workers. It supports JSON and pretty-printed output, stack traces, error formatting, custom transports, and sub-loggers. v5 adds an always-pretty default type (colorization and pretty.passObjectsNatively — on by default in real browsers — are the env-aware parts, never the format), flat fields-first JSON, async-context correlation, path/regex masking, a middleware chain, and pino/otel/genai presets. Current version: 5.x (the 5 line; _logMeta.v in JSON output is 5).
Settings are grouped (v5)
There are no flat settings keys. Configuration is organized into groups passed to new Logger({ ... }):
- Top-level:
type("json" | "pretty" | "hidden", defaults to"pretty"),name,minLevel(name or 0..6),prefix,customLevels,strictConfig,clock(injectable() => Date). mask: { keys, paths, regex, caseInsensitive, placeholder, censor }— redact secrets/PII/prompts by key, dotted path (*= one segment), or regex.json: { messageKey, levelKey, levelIdKey, timeKey, time, errorKey, numericLevel, stableKeyOrder }— structured-output key names/shape (time:"iso" | "epoch" | false | fn).pretty: { enabled, template, errorTemplate, style, timeZone, styles, levelMethod, inspectOptions, ... }.stack: { capture: "off" | "lazy" | "auto" | "full", internalFramePatterns }.meta: { property, attachContext }.
New runtime surface: getSubLogger/child (aliases), runInContext/getContext (AsyncLocalStorage correlation), attachTransport, use (middleware), flush, addLevel, isLevelEnabled, [Symbol.asyncDispose]/[Symbol.dispose], Logger.fromEnv, and the defineConfig helper. Presets ship as subpaths: tslog/presets/pino, tslog/otel, tslog/presets/genai; transports as tslog/transports/{file,http,ringbuffer}.
Quick Reference
npm install # Install dependencies
npm test # Run Vitest test suite
npm run test:browser # Run Playwright browser tests (Chromium, Firefox, WebKit)
npm run test:bun # Run Vitest under Bun
npm run test:deno # Build + run Deno test adapter
npm run build # Full build: types → ESM → browser IIFE bundle → prepare dist
npm run lint # Biome lint check
npm run format # Biome format all files
npm run check # Biome lint + format (write)
npm run coverage # Run tests with coverage report
npm run test:e2e-apps # Framework E2E: real Next.js (Turbopack) + TanStack Start dev servers (needs network + prior build)
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.
- yesterday First seen · 176 lines · 3,386 tokens per session scan A 0290cd4a9799
tslog AGENTS.md is an instructions file published in the GitHub repository fullstack-build/tslog (1,739 stars, last pushed 21d ago), licensed MIT. It adds 3,386 tokens to every session, about $0.0169 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
evlog AGENTS.md
Instructions for HugoRCD/evlog, covering evlog, commands, monorepo structure, conventions and code style: no slop.
stax CLAUDE.md
Instructions for cesarferreira/stax, covering claude.md, build & development commands, build debug version, build release version and run full test suite (preferred).
aistack AGENTS.md
Instructions for alp82/aistack, covering ai stack webapp, development process, prod database access, any convex cli command against prod, executed on the server and replace the local dev database with a fresh prod export.
stax AGENTS.md
Instructions for cesarferreira/stax, covering agents.md, harness: stax-dev, verification tiers, test command policy and why.
rsyslog copilot-instructions.md
Copilot instructions for rsyslog/rsyslog, a project described as: High-performance log ingestion and ETL engine.
rsyslog modules.plugins.instructions.md
Instructions for rsyslog/rsyslog, a project described as: High-performance log ingestion and ETL engine.