proposal-lint

A document checker for proposal files in a repository. It looks for outdated statuses, missing metadata, misplaced files, and other rule violations.

In plain words
What is it for?
Use it to check active and archived proposals, find stray files, produce a categorized report, and optionally move files or update their metadata after approval.
Why use it?
It removes the need to inspect every proposal by hand and helps keep proposal records consistent. It can report issues before applying approved fixes.

Command for Claude Code

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 commands/mendixlabs/mxcli/proposal-lint
Clone the repo
git clone --depth 1 https://github.com/mendixlabs/mxcli

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 870 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00013 $0.00870
Opus 5 $0.00006 $0.00435
Sonnet 5 $0.00003 $0.00174
Haiku 4.5 $0.00001 $0.00087

Measured yesterday against content hash da3dbc103463, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

proposal-lint 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 yesterday.

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.

.claude/commands/mxcli-dev/proposal-lint.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mxcli-dev:proposal-lint — Audit and Clean Up Proposals

Audit docs/11-proposals/ for status drift, missing frontmatter, misplaced files, and convention violations.

Read .claude/skills/lint-proposals.md first. It defines the frontmatter format, status vocabulary, and the seven lint rules. This command is the trigger; the skill is the contract.

Arguments

  • (no args) — run the lint, produce a report, stop.
  • --apply — only after the user has reviewed and approved the report: execute the proposed moves and frontmatter migrations.
  • --category <name> — limit the run to one category (e.g. frontmatter-missing, move-to-archive). Useful for incremental cleanup.

Process

Phase 1: Walk and check

  1. Walk docs/11-proposals/ and docs/11-proposals/archive/ (recursive).
  2. Scan /proposals/ at the repo root for stragglers.
  3. For each file, run rules R1–R7 from the skill.
  4. Collect findings into the eight categories defined in the skill.

Phase 2: Report

Print a structured report:

## Proposal lint report

Files scanned: NN active, MM archived, K strays
Total findings: XX

### move-to-archive (N)
- `PROPOSAL_xxx.md` — status: done; propose: git mv → archive/PROPOSAL_xxx.md
- ...

### frontmatter-missing (N)
- `proposal-yyy.md` — inline status "Draft" found; propose: add YAML frontmatter
- ...

### readme-drift (N)
- `archive/PROPOSAL_zzz.md` listed in README under Active section
- `PROPOSAL_aaa.md` exists on disk but missing from README
- ...

(etc. for each category)

Stop after the report. Do not modify files.

Phase 3: User direction

Ask the user:

  • Which categories to apply, and in what order?
  • Are there any flagged items to skip (e.g. a done proposal staying in active because work isn't fully finished, despite the inline status)?
  • Should naming-convention violations (R7) be ignored for now? (Default recommendation: yes.)

Phase 4: Apply (only with explicit approval)

For approved categories:

  1. Frontmatter migration: prepend YAML frontmatter to each file, preserving the inline **Status:** line for one cycle.
  2. Moves: use git mv so history is preserved. Update the README index to reflect new paths.
  3. Duplicate resolution: keep one canonical location; for the root /proposals/ stragglers, confirm with the user which to keep before removing.
  4. Supersession symmetry: add the missing direction (supersedes: / superseded-by:) to frontmatter.

Read the full file on GitHub · 104 lines

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. yesterday First seen · 104 lines · 13 tokens per session scan A da3dbc103463

Subscribe to this mod's changes

proposal-lint is a command published in the GitHub repository mendixlabs/mxcli (115 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13 tokens to every session and 870 once invoked, about $0.0001 per session on Opus 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.