Help us improve
Share bugs, ideas, or general feedback.
From tex-mex
Eval harness for mex-shaped scaffolds. Invoke when the user wants to measure whether a change to a mex scaffold (ROUTER.md, patterns/, context/, decisions.md) actually helps the agent. Asks two questions and runs a real eval.
npx claudepluginhub thedakshjaitly/tex --plugin tex-mexHow this skill is triggered — by the user, by Claude, or both
Slash command
/tex-mex:tex-mexThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are running as the `/tex-mex` skill. The user is iterating on a
Creates p5.js generative art with seeded randomness, noise fields, and interactive parameter exploration. Use for algorithmic art, flow fields, or particle systems.
Share bugs, ideas, or general feedback.
You are running as the /tex-mex skill. The user is iterating on a
mex-shaped scaffold (or any project with ROUTER.md / patterns/ /
context/ files) and wants measured evidence about whether their change
moved the needle. Not vibes. A real A/B run.
Your job is simple. Ask two questions, then do the work.
Free-form. The user might say:
patterns/idempotency.md and updated AGENTS.md to mention it"context/architecture.md into three smaller files"decisions.md"Listen for which files changed and what the user thinks the change should improve. You'll need both to scaffold useful tasks.
Offer these four options and let them pick:
| Option | Means |
|---|---|
| (a) Before my change | Stash the working tree → baseline run → un-stash → candidate run. Cleanest A/B; takes 2× the budget. |
| (b) Nothing at all (no scaffold) | Baseline with --subject none (bare agent, no scaffold loaded) → candidate with the scaffold present. Answers "does the scaffold help at all?" |
| (c) A specific other version | User points at a git commit or branch. Stash + check out → baseline → check back out → candidate. |
| (d) Just baseline | Single run, no diff. Useful for first-time setup; tells you what the agent's behavior looks like today. |
Default to (a) unless the user says otherwise.
Once you have answers to Q1 and Q2:
tex is availableThe plugin ships a shim at bin/tex (added to PATH automatically when the
plugin is enabled). The shim forwards to a copy of tex-eval installed
into ${CLAUDE_PLUGIN_DATA} by the plugin's SessionStart hook.
tex --version
If this fails with "tex-eval is not yet installed", the SessionStart hook didn't run yet — wait a moment and retry, or run the fallback the error message prints.
If the user has no corpus/ yet:
tex init --kind scaffold \
--var scaffold_name="<inferred from project>" \
--var scaffold_purpose="<inferred from README or user's answer>" \
--dir .
Then interview each task in corpus/01-*.yaml, 02-*.yaml,
03-*.yaml. For each:
Then validate:
tex validate corpus
If the user already has a corpus/, skip the init/interview unless they
ask for new tasks.
For option (a) "before my change":
# 1. Verify the working tree is clean enough to stash
git status
# 2. Stash the user's changes
git stash push -m "tex-mex-baseline-stash"
# 3. Run the baseline
tex run --label baseline-pre-change --subject scaffold --force
# 4. Restore
git stash pop
For option (b) "nothing at all":
tex run --label baseline-no-scaffold --subject none --force
For option (c) "specific other version":
git stash push -m "tex-mex-cand-stash"
git checkout <ref-the-user-named>
tex run --label baseline-<ref> --subject scaffold --force
git checkout -
git stash pop
For option (d) "just baseline": same as (a) but skip steps 2 and 4. No candidate run; jump to the summary.
tex run --label candidate-current --subject scaffold --force
(Skip if option (d).)
tex diff results/baseline-*/report.json results/candidate-*/report.json
Then summarize in plain English — don't dump the table at the user. Pick the headline:
tokens_loaded jumped 47%. Your scaffold's pitch is
less context, so the trade-off matters."End with the path to the saved report: "Full report at
results/candidate-current/report.md if you want the per-task table."
report.json after a run completes.--auth key. The user has a subscription; that's
the right path. If they want BYOK, they'll ask.fixtures/sample-target/ — the corpus
templates already work against . directly.tex-eval) supports those; this skill is mex-shaped on
purpose. If the user has a CLI they want evaluated, point them at the
tex-cli plugin (when it exists) or to tex init --kind cli directly.If the user wants something this skill doesn't do, drop to the underlying
tex CLI — tex --help shows the full command surface.