seeklink CLAUDE.md

A set of Claude Code instructions for the seeklink repository, including planning rules and guidance for requesting a second Codex review.

In plain words
What is it for?
Use it to plan non-trivial changes, recheck project state after interruptions, and request a fresh read-only Codex review of a code diff.
Why use it?
It keeps Claude Code’s workflow, project memory, and review process consistent across sessions.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/simonsysun/seeklink/claude-md
Clone the repo
git clone --depth 1 https://github.com/simonsysun/seeklink
Per session 225 This file is loaded in full into every session.
When invoked 225 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00225 $0.00225
Opus 5 $0.00112 $0.00112
Sonnet 5 $0.00045 $0.00045
Haiku 4.5 $0.00022 $0.00022

Measured 3d ago against content hash 9921fe6ee240, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seeklink CLAUDE.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 3d 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.

CLAUDE.md · 22 lines

What it actually says

@AGENTS.md

Claude Code only

  • Use plan mode before non-trivial code changes.
  • After compacting, clearing, resuming, or switching worktrees, re-read docs/current_focus.md and check git status.
  • For large or ambiguous features, interview first, write a short plan/spec, then implement from clean context when appropriate.
  • Do not use Claude auto-memory, skills, or hidden local notes as project truth. Durable project state belongs in repo files or git history.
  • Use skills for repeatable procedures, not for long-lived project state.

Claude-triggered Codex second review

When asking Codex for a second review, prefer a fresh ephemeral read-only run:

codex exec --ephemeral --sandbox read-only "Review the current diff against main. Focus on correctness, security, behavior regressions, and missing test coverage. Do not modify files."

Do not create or reuse a long-running Codex reviewer session.

Do not create a generic codex-review worktree.

Apply review fixes in the primary implementation session unless the human explicitly asks Codex to patch.

Changes

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.

  1. 3d ago First seen · 22 lines · 225 tokens per session scan A 9921fe6ee240

Subscribe to this mod's changes

seeklink CLAUDE.md is an instructions file published in the GitHub repository simonsysun/seeklink (11 stars, last pushed 2mo ago), licensed MIT. It adds 225 tokens to every session, about $0.0011 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.