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 skills/xcota/pos/enable-modulesnpx skills add xcota/pos --skill enable-modulesgit clone --depth 1 https://github.com/xcota/posWhat 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 | $0.00039 | $0.01195 |
| Opus 5 | $0.00019 | $0.00598 |
| Sonnet 5 | $0.00008 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade C, and why
enable-modules scanned grade C with 1 finding 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 2d ago.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
4. **Prune** (only with `--prune`, per disabled module): `rm -rf .claude/skills/<skill>/`. Never touch `modules/` (that's the source), never touch workspace dirs or seed data the user may have filled in — only the instal How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/enable-modules — file-based module installer
Reads modules.yaml at the vault root and installs every module marked enabled: true. Purely mechanical: copy a SKILL.md, make some dirs, copy some seed files. No DB, no registry, no daemons. Re-running is safe (idempotent overwrite).
Usage
/enable-modules — install all enabled: true modules
/enable-modules --prune — also remove .claude/skills/<skill>/ for every enabled: false module
/enable-modules --dry-run — print the plan (what would be copied/made/removed), change nothing
What a module is
modules.yaml lists each module. The manifest key (<name>) is the source folder modules/<name>/; the skill: field (<skill>) is the install target .claude/skills/<skill>/ — usually identical. Per entry:
enabled— install it or notskill— skill name; install target is.claude/skills/<skill>/dirs— vault-relative dirs to create (mkdir -p)seeds— starter files for the module. Each entry is the vault-relative destination; the source ismodules/<name>/seeds/<basename>. Copied only if the destination does not already exist (never clobber the user's data); if the source is absent, warn and continue.requires— a human precondition; print it, don't enforce it
The module's skill body lives at modules/<name>/SKILL.md (already sanitized, generic).
Steps
- Read
modules.yaml. If absent → tell the user, stop. - For each module, decide the action:
enabled: true→ installenabled: false→ skip (or remove if--prune)
- Install (per enabled module):
mkdir -p .claude/skills/<skill>- copy
modules/<name>/SKILL.md→.claude/skills/<skill>/SKILL.md - if
modules/<name>/references/exists, copy it alongside the SKILL.md mkdir -p <dir>for each entry indirs- for each
seed(destination path): source ismodules/<name>/seeds/<basename>. If the source exists AND the destination does not,mkdir -pthe dest parent and copy; if the dest already exists, skip (never overwrite user data); if the source is missing, print a one-line warning and continue - print the module's
requiresline as a reminder
- Prune (only with
--prune, per disabled module):rm -rf .claude/skills/<skill>/. Never touchmodules/(that's the source), never touch workspace dirs or seed data the user may have filled in — only the installed skill dir. - Report: one line per module —
installed | pruned | skipped | already-present— plus any seed warnings.
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.
- 2d ago First seen · 70 lines · 39 tokens per session scan C f2fce6add6ae
enable-modules is a skill published in the GitHub repository xcota/pos (52 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,195 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
rtg-knowledge-graph-mcp
Operate the Vellis RTG Knowledge Graph MCP server for agent-driven graph work. Use when an agent has RTG MCP tools such as rtgvalidategraph, rtgapplylivegraphchanges, rtgstageknowledgechanges, rtgapplymigrationcutover, rtgexecutequery, snapshots, or ledger replay, especially for schema evolution, validation recovery…
python-component-implementation
Implement, review, or revise Python realizations of components from accepted textual SysML v2 contracts and generated views. Use when creating or aligning Python protocols, component classes, reference implementations, implementation bindings, or black-box contract tests.
documentation-sync
Keep human documentation synchronized with canonical SysML v2 models, generated component and application views, implementation realizations, repository tooling, skills, and workflow rules. Use after model, code, generated-view, README, AGENTS, skill, command, or public behavior changes.
sysml-reference
Ground textual SysML v2 and KerML authoring, review, language-semantics decisions, construct selection, and official-validator diagnosis in the repository's checksum-pinned specification corpus. Use for questions or changes involving parts, references, features, actions, bindings, successions, flows, ports…
model-hygiene-review
Audit accepted SysML v2 component or application models against implementations, protocols, consumers, tests, generated evidence, predecessor contracts, and git history before proposing remediation. Use for periodic model hygiene, suspected model/implementation drift, migration-loss reviews, verification-closure…