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/kelesmert/turnlens/agents-mdgit clone --depth 1 https://github.com/kelesmert/turnlensWrote 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/kelesmert/turnlens/agents-md)<a href="https://agentmods.dev/instructions/kelesmert/turnlens/agents-md"><img src="https://agentmods.dev/badge/instructions/kelesmert/turnlens/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 | $0.02061 | $0.02061 |
| Opus 5 | $0.01030 | $0.01030 |
| Sonnet 5 | $0.00412 | $0.00412 |
| Haiku 4.5 | $0.00206 | $0.00206 |
Grade A, and why
turnlens 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 5d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TurnLens
Per-turn token and cost monitoring for AI coding agents. It answers one question that agent session files do not answer directly: what did this single prompt and its response cost?
TypeScript, ESM, zero runtime dependencies. This file holds what is worth knowing in every task; everything else is routed to below.
Commands
npm test vitest
npm run typecheck includes test/
npm run lint eslint, type-aware, src and test
npm run check the three above, in order
npm run build tsc, cleans dist/ first
npm run pricing:snapshot regenerates src/pricing/snapshot.generated.ts
npm run verify:costs cross-checks pricing against ccusage
lint runs itself: a Stop hook in .claude/settings.json blocks the end of
any turn that wrote a .ts file and left a lint error.
The user-facing surface is turnlens --help. It is not copied here, because a
copy is right until the next flag is added.
Skills
live-verification: checking TurnLens against live agent data, or taking any figure that will be treated as evidence.design-doc: designing work that this session will also implement.typescript-best-practices: writing, reviewing or refactoring.ts.
Open the file
Never write a claim about this code from memory. Not a return type, not a column count, not what a test file covers, not a line number. Open it. This costs seconds and the alternative has already cost a working day.
Measured on one design document, 11 August 2026: roughly half its defects were
sentences written without opening the source. formatCostUsd was described as
producing a number when it returns a toFixed(6) string. The CSV was called 24
columns when CSV_HEADER held 23 that day, which is the sort of figure that
rots: it is 24 now, and the point is that neither number was ever counted.
test/history.test.ts was named as covering readRecordedKeys on the strength
of its filename alone, when it tests formatHistoryBlock and never opens a CSV.
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.
- 5d ago First seen · 151 lines · 2,061 tokens per session scan A cf7bdfa429a0
turnlens AGENTS.md is an instructions file published in the GitHub repository kelesmert/turnlens (2 stars, last pushed 24d ago), licensed MIT. It adds 2,061 tokens to every session, about $0.0103 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 2026-08-31.
Other instructions, from other repositories
docvet CLAUDE.md
Claude Code instructions for Alberto-Codes/docvet, covering claude.md, project overview, build & development, install in development mode and with optional griffe support.
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.
agent-notify AGENTS.md
AGENTS.md instructions for Akash97p/agent-notify, covering agentnotify agent workflow, start or resume work, local git workflow, required quality gates and architecture and security guardrails.
coograph brutal-honesty.instructions.md
Global communication style — applies to all workspaces and conversations.
tidyfactor-design AGENTS.md
Instructions for alwkala/tidyfactor-design, covering ⚡ skill & 24 modular slash commands (7 lifecycle stages) and critical architecture (non-negotiable).
AmbyKit CLAUDE.md
Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.