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 skills add LLM-Coding/Semantic-Anchors --skill socratic-code-theory-recoverygit clone --depth 1 https://github.com/LLM-Coding/Semantic-AnchorsWrote 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/skills/llm-coding/semantic-anchors/socratic-code-theory-recovery)<a href="https://agentmods.dev/skills/llm-coding/semantic-anchors/socratic-code-theory-recovery"><img src="https://agentmods.dev/badge/skills/llm-coding/semantic-anchors/socratic-code-theory-recovery/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/skills/llm-coding/semantic-anchors/socratic-code-theory-recovery"><img src="https://agentmods.dev/badge/skills/llm-coding/semantic-anchors/socratic-code-theory-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00115 | $0.02598 |
| Opus 5.5 | $0.00046 | $0.01039 |
| Sonnet 5.5 | $0.00023 | $0.00520 |
| Haiku 4.5 | $0.00012 | $0.00260 |
Grade A, and why
socratic-code-theory-recovery 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Socratic Code-Theory Recovery
Reverse-engineer a bounded context into documentation without hallucinating the parts the code cannot tell you.
On invocation
When this skill is invoked:
-
Check whether the user named a bounded context. Look at the same message that invoked the skill and at the immediately preceding messages. A valid bounded-context pointer is a path (relative or absolute) to a directory, plus a short human-readable name for what the context is (e.g.
src/auth, "Authentication"). If both are present, proceed to Phase 1. -
If no bounded context is named, ask for it before doing anything else. Do not start Phase 1 against the current working directory by default — Phase 1 produces files (
QUESTION_TREE-<context-name>.adoc,OPEN_QUESTIONS-<context-name>.adoc) and running it on the wrong directory wastes work. Ask exactly:Which bounded context should I apply Socratic Code-Theory Recovery to? Give me a directory path (the bounded context's code root) and a short human-readable name. If you want the whole current repo treated as one bounded context, say so explicitly.
-
Once you have the pointer, run Phase 1. Use prompts/phase-1-question-tree.md — substitute
[bounded context path]with the user's path and[context-name]with the kebab-cased human-readable name. Do not change the leaf classification, Q-ID scheme, or the output-file naming scheme. -
Stop after Phase 1. Tell the user that Phase 1 is complete, where the two output files are, and that the next step is routing
OPEN_QUESTIONS-<context-name>.adocto the team. Phase 2 is gated on the file, not on being asked: before starting Phase 2 — even when the user explicitly requests it — check that every[OPEN]leaf inOPEN_QUESTIONS-<context-name>.adochas either a team answer or an explicit(deferred)marker. If any leaf has neither, do not run Phase 2; list the unanswered leaves instead.
When to use this skill
Use this skill on a brownfield codebase when:
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 134 lines · 115 tokens per session scan A 049ed1bedd29
socratic-code-theory-recovery is a skill published in the GitHub repository LLM-Coding/Semantic-Anchors (528 stars, last pushed today), licensed Apache-2.0. It adds 115 tokens to every session and 2,598 once invoked, about $0.0005 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.
Other skills, from other repositories
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
promptfoo-provider-setup
Connect Promptfoo to a model, live HTTP API, local Python/JavaScript provider, or app code. Use for request/auth mapping, response parsing, OpenAPI setup, and connection smoke tests. Use promptfoo-evals for broader eval coverage and promptfoo-redteam-setup for attack selection.
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
flux2-lora-training
Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks. Do not use for generic Stable Diffusion/DiT training, prompt authoring, or model serving; route those tasks to their specialized skill.
pixel-art-studio
A toolkit and workflow for creating pixel art, which is digital artwork made from deliberately placed, visible pixels. It supports static sprites, animations, sprite sheets, image conversion, palettes, and quality checks.
deep-review
Parallel competency-based code review. Launches independent Agent reviewers per competency (security, performance, architecture, database, concurrency, error-handling, frontend, testing), each with a focused checklist and isolated context. Synthesizes findings into unified report with FIX/DEFER/ACCEPT triage. Use…