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.
npx agentmods add commands/mendixlabs/mxcli/proposal-lintgit clone --depth 1 https://github.com/mendixlabs/mxcliWhat 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.
| Model | Per session | Once 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 |
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.
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
- Walk
docs/11-proposals/anddocs/11-proposals/archive/(recursive). - Scan
/proposals/at the repo root for stragglers. - For each file, run rules R1–R7 from the skill.
- 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
doneproposal 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:
- Frontmatter migration: prepend YAML frontmatter to each file,
preserving the inline
**Status:**line for one cycle. - Moves: use
git mvso history is preserved. Update the README index to reflect new paths. - Duplicate resolution: keep one canonical location; for the root
/proposals/stragglers, confirm with the user which to keep before removing. - Supersession symmetry: add the missing direction (
supersedes:/superseded-by:) to frontmatter.
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.
- yesterday First seen · 104 lines · 13 tokens per session scan A da3dbc103463
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.
Other commands, from other repositories
MIGRATE_DESIGN
Design doc for the migration tool PR. Author: Sol ([email protected]). Co-authored-by: wakesync.
plan
Create a structured task-by-task implementation plan for a feature and write it to docs/superpowers/plans/.
toh-help
Display all Toh Framework commands and quick usage guide.
specsmd-construction-agent
Command "specsmd-construction-agent" from fabriqaai/specs.md, covering activate construction agent, activation, parameters, critical first steps and your skills.
fire
FIRE orchestrator - Fast Intent-Run Engineering main entry point.
issue-resolve
Drive an assessed gflow-cli issue (verdict CONFIRMED-BUG or LIKELY-BUG, with localized verifiable scope) to a fix: isolated worktree off develop, test-first fix, /gflow:check, then a DRAFT PR for human review. Mutating and gated — runs inside a strict action envelope (never merges, never spends credits, never marks a…