Borrowing it
Nothing to install: this file belongs to tottinge/otter-kr. 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/tottinge/otter-kr/main/AGENTS.mdgit clone --depth 1 https://github.com/tottinge/otter-krWrote 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/tottinge/otter-kr/agents-md)<a href="https://agentmods.dev/instructions/tottinge/otter-kr/agents-md"><img src="https://agentmods.dev/badge/instructions/tottinge/otter-kr/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/tottinge/otter-kr/agents-md"><img src="https://agentmods.dev/badge/instructions/tottinge/otter-kr/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 | $0.00491 | $0.00491 |
| Opus 5.5 | $0.00196 | $0.00196 |
| Sonnet 5.5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
otter-kr 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 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.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository workflow
Use the atomic-commit skill for every commit. It is the authoritative
procedure for choosing a coherent batch, maintaining a green exact state,
resolving untracked files, reviewing the complete staged snapshot, obtaining
human approval, and verifying the post-commit workspace.
For this repository, treat the untracked-file disposition assessment as a hard safety boundary: every non-ignored path must be explicitly classified as add, gitignore, or delete, with the chosen action performed before staging. Ignored paths need not be listed unless the ignore rules are changing.
Do not assume a previously clean workspace is still clean without validating it.
TDD and refactoring slice gate
Every feature, fix, or characterization slice must make its evidence explicit:
- Before production edits, record the preflight scope, direct callers, and the smallest behavior to admit.
- Add or identify the focused test, run it against the unchanged production code, and record the failing (red) result. If no red result can be established, classify the work honestly as characterization, documentation, or a retrospective repair rather than claiming strict TDD.
- Make the smallest production change, run the focused test and the complete fast suite, and record the green result.
- Refactor the tests for resilient behavior (and the changed production code for representation) while green; then rerun the fast suite.
- Perform a scoped post-slice review covering the changed code, siblings, and callers. Record whether it found a follow-up or nothing to do.
Do not advance to the atomic-commit protocol until these checks are complete. The commit summary must state the slice, red/green evidence, test-refactor decision, post-slice review result, and untracked-file dispositions.
MCP support-process lifecycle
During an editing or TDD session, run at most one otter-kr support server. Check
for an existing server before starting it; do not launch additional one-shot
servers alongside the owned session. The session owner is responsible for
stopping the server in a finally/cleanup path before the commit protocol, then
verifying the process table contains no otter-kr or FastMCP leftovers. If a
child process survives shutdown, terminate that specific child immediately and
recheck before continuing.
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 · +21 lines · +241 tokens per session 34b3b08685e5
- 2mo ago First seen · 24 lines · 250 tokens per session scan A db364803c6b5
otter-kr AGENTS.md is an instructions file published in the GitHub repository tottinge/otter-kr (1 stars, last pushed 17d ago), licensed MIT. It adds 491 tokens to every session, about $0.0020 per session on Opus 5.5. 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.
otter-kr AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| otter-kr AGENTS.mdtottinge/otter-kr | Instructions file | 1 | 17d ago | MIT | A | 491 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |