Skip to content

InferHaven/agent-skills / codetrain

codetrain

Flagged

CodeTrain is an open-source Socratic coding tutor with a local lesson page where the learner writes every line while the agent sets small steps, gives hints and reviews the work without putting the solution into the lesson. Use when the user wants to be taught/walked through code one tiny step at a time — triggers like "teach me this code", "walk me through this", "hold my hand", "explain step by step", "tutor me", "guide me through", "I want to learn this", or asks for a safe practice exercise to learn a concept.

FileKindSize
LICENSEother11.1 KB
NOTICEother768 B
README.mdmarkdown22.7 KB
SKILL.mdskill md20.1 KB
app/answer_guard.pyscript7.8 KB
app/checkpoint-hook.shexecutablescript1.2 KB
app/ctl.shexecutablescript4.5 KB
app/install-permissions.pyscript6.8 KB
app/patch.pyexecutablescript4.1 KB
app/profile.pyexecutablescript9.3 KB
app/server.pyexecutablescript23.1 KB
app/static/Archivo.woff2binary88.0 KB
app/static/JetBrainsMono.woff2binary30.7 KB
app/static/app.jsscript57.1 KB
app/static/docklint.jsscript4.3 KB
app/static/editor.jsscript4.4 KB
app/static/fonts-OFL.txtmarkdown9.0 KB
app/static/glossary.jsscript50.8 KB
app/static/index.htmlother8.0 KB
app/static/js-worker.jsscript3.9 KB
app/static/liveness.jsscript1.8 KB
app/static/logo-anim.svgother1.9 KB
app/static/prism.jsscript20.6 KB
app/static/prose.jsscript18.8 KB
app/static/pyodide-worker.jsscript7.0 KB
app/static/runner.jsscript4.5 KB
app/static/sheet.cssother32.7 KB
app/static/styles.cssother51.4 KB
app/static/theme-toggle.jsscript9.5 KB
app/static/theme.jsscript5.2 KB
app/static/visuals.jsscript14.8 KB
app/watch.shexecutablescript2.5 KB
install.shexecutablescript2.0 KB
references/session-protocol.mdmarkdown19.6 KB
references/spaced-repetition.mdmarkdown3.4 KB
references/teach-on-diff.mdmarkdown2.5 KB

app/patch.py

View on GitHub
#!/usr/bin/env python3
"""CodeTrain — apply a small JSON delta to session.json.

Lets the tutor update a session with only the CHANGED fields, instead of reading +
rewriting the whole file each turn — the main token saver.

The delta is read from (in priority order):
  1. <session-dir>/patch.json  — the tutor writes this with the Write tool, then runs
     `bash ctl.sh patch <ws>`. This is the robust path: no shell quoting (JSON with
     `(`, quotes, or newlines just works) and no permission prompt. patch.json is
     deleted after a successful apply.
  2. argv[2]                   — a delta passed as an arg (fragile with quotes; back-compat).
  3. stdin                     — a piped delta (back-compat).

Special keys (processed, then removed):
  clear_inbox    : true           -> set inbox = []
  learned_append : str | [str]    -> append to learned[]
  steps_append   : {…} | [{…}]    -> append new step(s) to steps[] (lazy authoring)
  step_patch     : {index?, ...}   -> merge into steps[index | active]; APPENDS if the
                                      index is out of range (never silently dropped)
Dotted top-level keys are expanded ("progress.step": 1 -> {"progress": {"step": 1}}),
so a model that flattens keys still patches correctly. Everything else is deep-merged
(dict -> recursive; else replace).

Usage:  patch.py <session.json> ['<delta>']
"""
import json
import os
import sys


def merge(dst, src):
    for k, v in src.items():
        if isinstance(v, dict) and isinstance(dst.get(k), dict):
            merge(dst[k], v)
        else:
            dst[k] = v
    return dst


def expand_dotted(d):
    """{"a.b": 1, "x": 2} -> {"a": {"b": 1}, "x": 2}  (top-level dotted keys only)."""
    out = {}
    for k, v in d.items():
        if isinstance(k, str) and "." in k:
            cur = out
            parts = k.split(".")
            for p in parts[:-1]:
                nxt = cur.get(p)
                if not isinstance(nxt, dict):
                    nxt = {}
                    cur[p] = nxt
                cur = nxt
            cur[parts[-1]] = v
        else:
            out[k] = v
    return out


def main():
    if len(sys.argv) < 2:
        print("usage: patch.py <session.json> ['<delta>']", file=sys.stderr)
        sys.exit(2)
    path = sys.argv[1]
    patch_file = os.path.join(os.path.dirname(path), "patch.json")

    used_file = False
    if os.path.exists(patch_file):
        with open(patch_file, "r", encoding="utf-8") as f:
            raw = f.read()
        used_file = True
    elif len(sys.argv) > 2 and sys.argv[2].strip():
        raw = sys.argv[2]
    else:
        raw = sys.stdin.read()
    delta = json.loads(raw or "{}")

    with open(path, "r", encoding="utf-8") as f:
        s = json.load(f)

    if delta.pop("clear_inbox", False):
        s["inbox"] = []
    if "learned_append" in delta:
        add = delta.pop("learned_append")
        s.setdefault("learned", [])
        s["learned"].extend(add if isinstance(add, list) else [add])
    if "steps_append" in delta:
        add = delta.pop("steps_append")
        s.setdefault("steps", [])
        if isinstance(s["steps"], list):
            s["steps"].extend(add if isinstance(add, list) else [add])
    if "step_patch" in delta:
        sp = dict(delta.pop("step_patch"))
        idx = sp.pop("index", None)
        steps = s.get("steps")
        if isinstance(steps, list):
            if idx is None:
                idx = ((s.get("progress") or {}).get("step", 1) or 1) - 1
            if 0 <= idx < len(steps):
                merge(steps[idx], sp)
            else:                       # out of range -> append; NEVER silently drop
                steps.append(sp)
        elif isinstance(s.get("step"), dict):
            merge(s["step"], sp)
        else:
            s["steps"] = [sp]

    merge(s, expand_dotted(delta))

    tmp = path + ".tmp"
    with open(tmp, "w", encoding="utf-8") as f:
        json.dump(s, f, indent=2)
    os.replace(tmp, path)
    if used_file:
        try:
            os.remove(patch_file)
        except OSError:
            pass
    print("patched (steps=%d)" % len(s.get("steps") or []))


if __name__ == "__main__":
    main()
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall