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/tetracoralla/context-surface-analyzer/agents-mdgit clone --depth 1 https://github.com/tetracoralla/context-surface-analyzerWrote 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/tetracoralla/context-surface-analyzer/agents-md)<a href="https://agentmods.dev/instructions/tetracoralla/context-surface-analyzer/agents-md"><img src="https://agentmods.dev/badge/instructions/tetracoralla/context-surface-analyzer/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 | $0.00479 | $0.00479 |
| Opus 5 | $0.00239 | $0.00239 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
context-surface-analyzer 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 4d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Surface Analyzer repository contract
This repository is an independent provider product. Read docs/PRODUCT_MODEL.md
and docs/REVIEW_CONTRACT.md before changing behavior, schemas, limits, or
claims.
Authority and boundaries
- Current source, executable tests, and current CLI/MCP/web runtime control factual claims. Generated reports do not certify utility, safety, adoption, or completeness.
- The shared core in
src/core.jsowns analysis and comparison semantics. CLI, MCP, and web routes are adapters and must not independently implement them. - Inputs are explicit bounded snapshots. Do not add passive observation, filesystem crawling, host discovery, credentials, network calls, model calls, automatic routing, enable/disable actions, or retirement recommendations.
- Exact UTF-8 byte counts are for canonical JSON defined by this product. They are not token estimates. Token measurements are caller-supplied observations and remain labeled by source, provider, model, serialization, and tokenizer version when supplied.
- Name collisions are exact and case-sensitive. Duplicate schemas require exact canonical equality. Do not silently upgrade these observations into semantic similarity or product value judgments.
- This MVP declares no provider-neutral Capability Profile or Procedure Profile. Do not create one without a separate standardization decision.
Change rules
- Keep snapshot fields and transport arguments closed and reject unknown keys.
- Keep all requests and complete responses cumulatively bounded. Every relaxed limit requires a current consumer and a negative regression test.
- Preserve one-call dominant Agent routes:
context.analyzeandcontext.diff. - Keep MCP annotations read-only, non-destructive, idempotent, and closed-world.
- Keep the MCP carrier's 2025 legacy-era boundary explicit. Do not advertise 2026 modern-era support without the required per-era negotiation and wire codec through a portable installed runtime.
- Keep the human surface local, narrow, and free of Agent protocol metadata.
- Add the smallest negative regression for every repaired guard or ambiguity.
- Do not commit, push, publish, install globally, or edit a sibling repository without explicit owner authorization.
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.
- 4d ago First seen · 44 lines · 479 tokens per session scan A 739d062b664c
context-surface-analyzer AGENTS.md is an instructions file published in the GitHub repository tetracoralla/context-surface-analyzer (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 479 tokens to every session, about $0.0024 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
Octop AGENTS.md
AGENTS.md instructions for TencentCloud/Octop, covering agents.md, 1. collaboration principles, think before writing, simplicity first and surgical edits.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
Lody AGENTS.md
AGENTS.md instructions for LodyAI/Lody, covering repository guidelines, context maintenance, repository boundary, project map and checks and commits.
Knote AGENTS.md
Instructions for 1661169091kiwi/Knote, covering agents.md, 构建与验证约定（用户明确要求，所有会话必须遵守） and 测试说明.
Vibelution AGENTS.md
AGENTS.md instructions for CCDawn/Vibelution, covering vibelution agent rules, 1. identity and priority, 2. global red lines, 3. start and routing and 3.0 每任务先 router.
dev-report-weekly AGENTS.md
Instructions for JYYYYYT/dev-report-weekly, covering devweek contribution guide, product boundary, frozen visual direction, trust and privacy and quality gates.