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/romiluz13/cc10x/updatenpx skills add romiluz13/cc10x --skill updategit clone --depth 1 https://github.com/romiluz13/cc10xWhat 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 | $0.00097 | $0.01150 |
| Opus 5 | $0.00048 | $0.00575 |
| Sonnet 5 | $0.00019 | $0.00230 |
| Haiku 4.5 | $0.00010 | $0.00115 |
Grade C, and why
update scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
5. Clean up: `rm -rf "$CACHE_ROOT.old"` (only after user confirms) How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cc10x Update
Safe upgrade that preserves your local modifications to cached skill files.
Workflow: Discover versions → Stash local diffs → Pull upstream → Rebuild cache → Rebase patches → Verify.
Paths (Resolve Once)
REGISTRY="$HOME/.claude/plugins/installed_plugins.json"
KNOWN_MARKETPLACES="$HOME/.claude/plugins/known_marketplaces.json"
CACHE_ROOT="$HOME/.claude/plugins/cache/cc10x/cc10x"
BACKUP_DIR="$HOME/.claude/plugins/cache/cc10x/_backup_$(date +%Y%m%d_%H%M%S)"
Read installed_plugins.json → extract cc10x@cc10x entry. If missing → STOP.
Read known_marketplaces.json → extract cc10x.installLocation → MARKETPLACE_ROOT.
Verify $MARKETPLACE_ROOT/.git exists. If missing → STOP.
On any STOP, report which prerequisite is absent (registry entry / marketplace git checkout) and that reinstalling the plugin restores it — a bare STOP leaves the user with no path forward.
Phase 1: Discovery
- Read installed version from registry entry
- Read marketplace version from
$MARKETPLACE_ROOT/plugins/cc10x/.claude-plugin/plugin.json - Check upstream:
cd "$MARKETPLACE_ROOT" && git fetch origin && git log HEAD..origin/HEAD --oneline - Display: installed version, marketplace version, commits behind
- Gate: if no updates → STOP. If updates available → ask user to proceed.
Phase 2: Stash Local Modifications
-
Enumerate cache files:
find "$CACHE_ROOT" -type f \( -name "*.md" -o -name "*.json" -o -name "*.py" \) | sort -
For each cached file, diff against marketplace source (pristine → locally-modified, so applying the patch later re-adds your changes):
diff -u "$MARKETPLACE_ROOT/plugins/cc10x/$file" "$CACHE_ROOT/$file" -
If diffs found → save to
$BACKUP_DIR/patches/as.patchfiles. Report which files have local modifications. -
Also check for user-added files (in cache but not in marketplace):
comm -23 <(cd "$CACHE_ROOT" && find . -type f | sort) <(cd "$MARKETPLACE_ROOT/plugins/cc10x" && find . -type f | sort) -
Copy user-added files to
$BACKUP_DIR/user-files/
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 · 85 lines · 97 tokens per session scan C 17e70cd3fab6
update is a skill published in the GitHub repository romiluz13/cc10x (164 stars, last pushed 29d ago), licensed MIT. It adds 97 tokens to every session and 1,150 once invoked, about $0.0005 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
create-request
Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /req-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard.…
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
codex-code-review
Code review using Codex MCP. Use when: PR review, code audit, second opinion on changes. Not for: doc review (use doc-review), security audit (use security-review). Output: severity-grouped findings + merge gate.
meta-harness-terminal-bench-2
Run one iteration of AgentHarness evolution for Terminal-Bench 2.
meta-harness
Run one iteration of memory system evolution. Called by metaharness.py or interactively via /meta-harness.
adr
Write an Architecture Decision Record (ADR) for a feature — Context / Decision / Status / Consequences / Alternatives, filed as docs/features/ /adr- - .md with a 3-digit zero-padded number. Handles the Superseded case: bidirectional linking when a new ADR replaces an old one. Use when: recording why an architectural…