Borrowing it
Nothing to install: this file belongs to intertwine/dspy-agent-skills. 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/intertwine/dspy-agent-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/intertwine/dspy-agent-skillsWrote 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/intertwine/dspy-agent-skills/claude-md)<a href="https://agentmods.dev/instructions/intertwine/dspy-agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/intertwine/dspy-agent-skills/claude-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/intertwine/dspy-agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/intertwine/dspy-agent-skills/claude-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 | $0.01158 | $0.01158 |
| Opus 5.5 | $0.00463 | $0.00463 |
| Sonnet 5.5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
dspy-agent-skills CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code (or any agent) working inside this repo.
What this repo is
A pack of agent skills that teaches coding agents to build, optimize, and ship DSPy 3.2.x programs. It is designed to install cleanly into both Claude Code (~/.claude/skills/) and Codex CLI (~/.agents/skills/).
The skills themselves are in skills/<name>/SKILL.md. The product is Markdown; Python files in skills/*/example_*.py are runnable smoke tests, not library code.
Commands you'll actually run
# Validate all skill metadata, manifests, example syntax, and skill-doc correctness
uv run --with pytest python -m pytest tests/ -v
# Smoke-test every example offline (no API key needed)
for f in skills/*/example_*.py; do uv run --with dspy python "$f" --dry-run; done
# Validate the live DSPy API surface taught by these skills
env -u UV_EXCLUDE_NEWER uv run --with dspy==3.2.1 python scripts/check_dspy_surface.py
# Install skills locally into Claude Code and Codex (symlinks, idempotent)
./scripts/install.sh
# Uninstall
./scripts/install.sh --uninstall
# Live GEPA run (requires OPENAI_API_KEY)
cd skills/dspy-advanced-workflow
OPENAI_API_KEY=... uv run --with dspy python example_pipeline.py --auto light
If uv run --with dspy unexpectedly resolves an older DSPy release, check for UV_EXCLUDE_NEWER or another resolver policy that hides recent uploads. For an exact DSPy 3.2.1 validation run, use:
env -u UV_EXCLUDE_NEWER uv run --with dspy==3.2.1 python -c 'import dspy; print(dspy.__version__)'
Authoring / editing conventions
SKILL.md frontmatter — spec-only fields
Claude Code and Codex both follow the agentskills.io spec. Only these fields are honored in SKILL.md frontmatter:
name(required, kebab-case, ≤64 chars, must equal the parent directory name)description(required; combined withwhen_to_usemust stay ≤1536 chars)when_to_use,argument-hint,disable-model-invocation,user-invocable,allowed-tools,model,effort,context,agent,hooks,paths,shell
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.
- 2mo ago Changed · -16 lines · -205 tokens per session af1264a667a2
- 2mo ago First seen · 106 lines · 1,363 tokens per session scan A 474352058151
dspy-agent-skills CLAUDE.md is an instructions file published in the GitHub repository intertwine/dspy-agent-skills (278 stars, last pushed 2mo ago), licensed MIT. It adds 1,158 tokens to every session, about $0.0046 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 2026-08-30.
dspy-agent-skills CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dspy-agent-skills CLAUDE.mdintertwine/dspy-agent-skills | Instructions file | 278 | 2mo ago | MIT | A | 1,158 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |