mthds-fix

name	mthds-fix
description	Fix issues in MTHDS bundles. Use when user says "fix this workflow", "fix this method", "repair validation errors", "the pipeline is broken", "fix the .mthds file", after /mthds-check found issues, or when validation reports errors. Automatically applies fixes and re-validates in a loop.
min_mthds_version	0.12.1

Fix MTHDS bundles

Automatically fix issues in MTHDS method bundles.

Process

Step 0 — Environment Check (mandatory, do this FIRST)

Run this command to check toolchain status:

# Wrapped in `bash -c` so the bash array syntax below works even when the
# session shell is zsh (Codex runs blocks under the user's shell).
bash -c '
# Pick the cached env-check from the plugin version with the highest semver.
# Pad each numeric segment to fixed width so lex sort matches semver sort
# (avoids the 0.10 < 0.9 lex-order trap). Sort keys are digits-only by
# construction, so the [[ > ]] compare is locale-independent. Bash 3.2 OK.
_best_f=""; _best_k=""
for f in "${CODEX_HOME:-$HOME/.codex}"/plugins/cache/*/mthds/*/bin/mthds-env-check; do
  [ -x "$f" ] || continue
  _v="${f%/bin/*}"; _v="${_v##*/}"
  _k=""; IFS=. read -ra _parts <<<"${_v%%[-+]*}"
  for _p in "${_parts[@]}"; do _p=${_p%%[!0-9]*}; _k="${_k}$(printf %06d "${_p:-0}")"; done
  [[ "$_k" > "$_best_k" ]] && { _best_f="$f"; _best_k="$_k"; }
done
[ -n "$_best_f" ] && exec "$_best_f" "0.12.1" --codex
echo "MTHDS_ENV_CHECK_MISSING"
'

Interpret the output:

• MTHDS_AGENT_MISSING → STOP. Do not proceed. Tell the user:

The mthds-agent CLI is required but not installed. Install it with:

npm install -g mthds

Then re-run this skill.

• MTHDS_AGENT_VERSION_UNKNOWN → STOP. The installed mthds-agent returned an unparseable version. Tell the user:

Could not parse the output of mthds-agent --version. Your installation may be corrupt. Reinstall with:

npm install -g mthds@latest

Then re-run this skill.

• MTHDS_AGENT_OUTDATED <installed> <required> → The installed mthds-agent is too old for this plugin. Do not hard-stop. Instead, tell the user their mthds-agent (v<installed>) is older than the required v<required>, then follow the upgrade flow to offer upgrading mthds-agent via npm install -g mthds@latest. After the upgrade flow completes (whether the user upgraded or declined), proceed to Step 1. The upgrade flow's "Not now" and "Never ask" options let users continue with current versions.

• MTHDS_UPDATE_CHECK_FAILED ... → WARN. The update check command failed. Show the error output to the user. Suggest checking network connectivity and mthds-agent installation. Proceed to Step 1 with current versions.

• UPGRADE_AVAILABLE ... → Read upgrade flow and follow the upgrade prompts before continuing to Step 1.

• JUST_UPGRADED ... → Announce what was upgraded to the user, then continue to Step 1.

• UP_TO_DATE ... → Proceed to Step 1. The line is a terse list of verified installed versions (e.g. UP_TO_DATE mthds-agent=0.10.0 plxt=0.4.0 plugin=0.12.0); if you mention the env-check in your preamble acknowledgement, relay the agent and plugin versions you saw. Two "explicit-quiet" variants share the same prefix and are also clean — proceed to Step 1 without warning, and do not relay the quiet state unless the user is troubleshooting:

  • UP_TO_DATE update-check=disabled — the user has turned update-check off via config.
  • UP_TO_DATE update-check=snoozed — the user has an active snooze on the current version key; an upgrade would otherwise be available, but they explicitly asked for quiet.

• No output → WARN. The env-check produced no output at all, which usually means mthds-agent itself is broken or the wrapper script bailed before printing. Tell the user the environment check could not be confirmed, then proceed cautiously to Step 1.

• MTHDS_ENV_CHECK_MISSING → WARN. The env-check script was not found at either expected path. Tell the user the environment check could not run, but proceed to Step 1.

• CODEX_CONFIG_NEEDS_SETUP → Codex's ~/.codex/ is not set up for the mthds plugin, so the bundled .mthds validation hook will not load. When this fires it is the only terminal status the env-check emits — update-check is skipped entirely (not run, not suppressed) because fixing the hook is the prerequisite and update-check's upgrade marker is one-shot; the user re-runs and gets fresh update info next time. The env-check may print one or more #-prefixed diagnostic lines after the status — relay them if present. Resolve this before Step 1:

  1. Preview — run mthds-agent codex apply-config --dry-run and show the user the output. WOULD_APPLY lists the keys it will add under applied; ALREADY_OK means no keys need adding. Either way, relay any warnings entries — those (e.g. read-only sandbox, hooks disabled) need a hand-fix apply-config will not perform. If ALREADY_OK with no warnings, treat as resolved and go to Step 1.
  2. Ask — use AskUserQuestion: "Apply Codex config now?" with options "Apply now" / "Skip".
  3. Apply now — run mthds-agent codex apply-config:
     • APPLIED / ALREADY_OK → tell the user the config is fixed and they must restart Codex for the validation hook to load (it will not load in this session). Relay any warnings — those still need a hand-fix.
     • Error about conflicting keys → show it verbatim; the user must hand-edit ~/.codex/config.toml, then re-run mthds-agent codex apply-config.
     • Error from the sandbox blocking the write to ~/.codex/config.toml → ask the user to run mthds-agent codex apply-config themselves in a terminal, then restart Codex.
  4. Skip — tell the user the validation hook stays off until they run mthds-agent codex apply-config and restart Codex.

  Then proceed to Step 1. This session has no PostToolUse hook. The mthds skills still run mthds-agent validate bundle explicitly, so .mthds files built or edited through a skill are still semantically validated — but the write-time plxt lint/fmt pass depends on the hook and will not run until Codex is restarted.

• Any other output → WARN. The preamble produced unexpected output. Show it to the user verbatim. Proceed to Step 1 cautiously.

Do not write .mthds files manually, do not do any other work. The CLI is required for validation, formatting, and execution — without it the output will be broken.

No backend setup needed: This skill works without configuring inference backends or API keys. You can start building/validating methods right away. Backend configuration is only needed to run methods with live inference — use /mthds-runner-setup when you're ready.

Step 1: Validate and Identify Errors

Always use -L pointing to the bundle's own directory to avoid namespace collisions:

mthds-agent validate bundle <file>.mthds -L <bundle-directory>/

Parse the JSON output:

• If success: true — nothing to fix, report clean status
• If error_type: "ValidateBundleError" — iterate through validation_errors array and fix each (Step 2)
• If model/config error — see Error Handling Reference (cannot be fixed by editing the .mthds file)

Step 2: Fix .mthds Validation Errors

Use the error_type field from each validation error to determine the fix:

Error Type	Fix Strategy
missing_input_variable	Add the missing variable(s) to the parent pipe's inputs line
extraneous_input_variable	Remove the unused variable(s) from the pipe's inputs line
input_stuff_spec_mismatch	Correct the concept type in inputs to match what the sub-pipe expects
inadequate_output_concept	Change the output field to the correct concept type
inadequate_output_multiplicity	Add or remove [] from the output concept
circular_dependency_error	Restructure the method to break the cycle
llm_output_cannot_be_image	Use PipeImgGen instead of PipeLLM for image generation
invalid_pipe_code_syntax	Rename the pipe to valid snake_case
unknown_concept	Add the concept definition to the bundle, or fix the typo
batch_item_name_collision	Rename input_item_name (or batch_as) to a distinct singular form of the list name. Also update the branch pipe's inputs to use the new item name.

For error type descriptions, see Error Handling — Validation Error Types.

Step 3: Fix TOML Formatting Issues

After applying semantic fixes, run mthds-agent plxt lint <file>.mthds as a quick TOML/schema correctness check. If lint passes, run mthds-agent plxt fmt <file>.mthds to auto-format the file before re-validating semantically in the next step.

Beyond what plxt catches, watch for these common issues:

Multi-line inputs — must be on a single line:

# WRONG
inputs = {
    a = "A",
    b = "B"
}

# CORRECT
inputs = { a = "A", b = "B" }

Pipe ordering — controllers before sub-pipes:

# CORRECT: main pipe first, then sub-pipes in execution order
[pipe.main_workflow]
type = "PipeSequence"
steps = [
    { pipe = "step_one", result = "intermediate" },
    { pipe = "step_two", result = "final" }
]

[pipe.step_one]
...

[pipe.step_two]
...

Missing required fields — add with sensible defaults:

• description on every pipe and concept
• type on every pipe
• output on every pipe

Step 4: Re-validate

After applying fixes, re-validate:

mthds-agent validate bundle <file>.mthds -L <bundle-directory>/

Continue the fix-validate loop until success: true is returned. Some fixes reveal new issues — for example, fixing a missing_input_variable may expose an input_stuff_spec_mismatch on the newly added input.

On the final successful validation, re-run with --graph to generate a flowchart:

mthds-agent validate bundle <file>.mthds -L <bundle-directory>/ --graph

Step 5: Report Results

• List all changes made (which pipes were modified and how)
• Show the final validation result
• Flag any remaining warnings or suggestions
• Mention the generated dry_run.html flowchart next to the bundle

Reference

• Error Handling — read when CLI returns an error to determine recovery
• MTHDS Agent Guide — read for CLI command syntax or output format details
• MTHDS Language Reference — read when writing or modifying .mthds TOML syntax
• Native Content Types — read when fixing type mismatches involving native concepts, to verify available attributes