exact-coding-baseline-export

A workflow for turning current research into a dated, consumer-ready exact-coding baseline. It applies defined changes to a source workflow and saves the result in a new export folder without changing the source.

In plain words
What is it for?
Use it to export a selected or automatically detected coding workflow into a dated directory, with one output subtree for each supported coding harness.
Why use it?
It keeps the original workflow intact while producing a version that can be used outside the research process. It also prevents accidental replacement of an existing snapshot for the same date.

Skill for Claude CodeCodex

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 skills/marcoemrich/agentic_coding_lab/exact-coding-baseline-export
Any agent
npx skills add marcoemrich/agentic_coding_lab --skill exact-coding-baseline-export
Clone the repo
git clone --depth 1 https://github.com/marcoemrich/agentic_coding_lab

Made for: Claude Code, Codex.

Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,894 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00157 $0.13894
Opus 5 $0.00078 $0.06947
Sonnet 5 $0.00031 $0.02779
Haiku 4.5 $0.00016 $0.01389

Measured 2d ago against content hash b047095c7b21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

exact-coding-baseline-export scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -rl '@\.claude/rules/' "$TARGET/.claude" | while read -r p; do
.claude/skills/exact-coding-baseline-export/SKILL.md · 1,162 lines

How it starts

The opening of the file, as written. The whole thing — 1,162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: exact-coding-baseline-export

Mint a dated, consumer-ready snapshot of the current best TDD workflow into research/workflow-dev/export/exact-coding-baseline-<YYYY-MM-DD>/.

This is a true transformation skill — it reads a source workflow (immutable) and applies three transformations on top of it (see "The three transformations" below), writing the result as a new snapshot. The skill is self-contained: the HITL consumable template and the README template live alongside this file under templates/, and the harness research lives in HARNESS-MECHANISMS.md.

Scope

  • Single repo: agentic_coding_lab_project. Writes only inside research/workflow-dev/export/. Does not touch source workflows under experiments/workflows/, consumer repos, or anything else.
  • Single artifact: a new directory at research/workflow-dev/export/exact-coding-baseline-<DATE>/, containing one subtree per exported harness.
  • Idempotent within a date: refuses to overwrite an existing same-date snapshot unless the user explicitly says "overwrite" / "force".

The three transformations

The export is not a copy. A lab workflow and a consumer workflow differ on three independent axes, and every export applies all three:

# Axis Lab Export
1 Lab content autonomy mandate, done-marker, phase-continuation fix removed (drop lab-only.md / strip LAB-ONLY fences)
2 Human checkpoints none — runs unattended HITL checkpoints, default level full-hitl
3 Invocation auto-loads on every session explicitly invoked by the user

Axis 3 is the one most easily forgotten, and it is harness-specific. A consumer fixing a typo must not get Red-Green-Refactor discipline in context; they should have to ask for the workflow. Mechanisms per harness are documented in HARNESS-MECHANISMS.mdread it before exporting a harness you have not exported before.

Arguments

Three, all optional:

  1. Date in YYYY-MM-DD form. Default: today (date +%F).
  2. Source workflow name (e.g. v6.6-lab-split-cc). Default: auto-detect (see "Source detection" below).
  3. Harness set: any of cc, pi, oc, cursor, or all. Default: cc.

Read the full file on GitHub · 1,162 lines

Files

What ships with it

5 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.

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. 2d ago First seen · 1,162 lines · 157 tokens per session scan B b047095c7b21

Subscribe to this mod's changes

exact-coding-baseline-export is a skill published in the GitHub repository marcoemrich/agentic_coding_lab (11 stars, last pushed 16d ago), licensed MIT. It adds 157 tokens to every session and 13,894 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens