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 skills add OutlineDriven/odin-codex-plugin --skill deps-upgradegit clone --depth 1 https://github.com/OutlineDriven/odin-codex-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/deps-upgrade)<a href="https://agentmods.dev/skills/outlinedriven/odin-codex-plugin/deps-upgrade"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-codex-plugin/deps-upgrade.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.01520 |
| Opus 5 | $0.00034 | $0.00760 |
| Sonnet 5 | $0.00014 | $0.00304 |
| Haiku 4.5 | $0.00007 | $0.00152 |
Grade A, and why
deps-upgrade 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 7d 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.
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.
This is a copy
88% identical to deps-upgrade — 121 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependencies are inherited code. Upgrades are inherited risk. Patch in batch, minor in batch with a smoke test, major one-at-a-time with a CHANGELOG read.
When to Apply / NOT
Apply: CVE remediation; major upstream release; compatibility forcing function; quarterly hygiene cadence; pre-release lockfile audit; deprecation warnings accumulating.
NOT apply: active feature branch with high churn; pre-release freeze window; mid-incident; API-break-driven refactor.
Anti-patterns
- Big-bang upgrade: bumping every dep at once.
- Skipping the lockfile: floating ranges create non-reproducible builds.
- Ignoring the CHANGELOG: major bumps without reading upstream notes.
- Suppressing deprecations:
--warning-as-error=offdefers cost. - Bypassing audit signals:
npm audit fix --forcewithout reading. - No smoke test on minor: minor versions can introduce behavior shifts.
- Forgetting transitives: surface deps look fine; transitive CVE remains.
- Mixing concerns in one commit: upgrade + refactor + feature — atomize per
<git>policy.
Workflow (language-neutral)
-
Inventory — enumerate manifests + lockfiles across ecosystems. Many canonical names are extensionless (
go.mod,Gemfile,pom.xml); filtering by extension alone misses them.fdonly takes one glob per call, so anchor on canonical filenames via a single regex:fd -t f '^(package(-lock)?\.json|pnpm-lock\.yaml|yarn\.lock|Cargo\.(toml|lock)|pyproject\.toml|poetry\.lock|requirements.*\.txt|Pipfile\.lock|go\.(mod|sum)|pom\.xml|build\.gradle(\.kts)?|settings\.gradle(\.kts)?|libs\.versions\.toml|gradle\.lockfile|Gemfile(\.lock)?|.*\.gemspec|.*\.opam|dune-project|opam\.locked|mix\.(exs|lock)|composer\.(json|lock))$'Add ecosystem-specific names if the project uses something rarer (
Pipfile,Brewfile,flake.nix,shard.yml,pubspec.yaml). Capture a lockfile snapshot for later diff (difft). -
Scan outdated — run ecosystem outdated/upgradable command. Capture report.
-
Categorize — bin every candidate as patch / minor / major.
-
Patch batch — bump all patches at once; lockfile-only diff. Run full test suite. Commit
chore(deps): patch sweep. -
Minor batch — bump minors together; smoke-test. Read each minor CHANGELOG. Commit
chore(deps): minor sweep. -
Major individually — one major version per commit. Read CHANGELOG / migration guide first; apply codemod or manual edits; run full suite + adversarial tests. Commit
chore(deps)!: bump <pkg> <old>→<new>. -
Lockfile audit — compare pre/post with
difft(notdiff). Check transitive churn. -
Re-scan — run CVE scanner again post-upgrade.
-
Hand off — major upgrade requires API-break propagation → cross to a refactor / break-compat workflow. New CVEs → hand to security-audit workflow.
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.
- 7d ago First seen · 86 lines · 68 tokens per session scan A ac091d74a7fc
deps-upgrade is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (15 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,520 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to deps-upgrade, differing in 121 lines, and is treated as a copy.
Other skills, from other repositories
git-guardrails-claude-code
Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.
duet
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.
explore
Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Uses a staged 1/3/5 Explore-agent escalation protocol scaled to scope.…
deps-upgrade
Dependency-upgrade campaign — outdated scan, batch-by-severity, breaking-change remediation, lockfile audit. Use when CVEs require remediation, when a major upstream version lands, when stack compatibility forces a sweep, or on a scheduled (quarterly) hygiene cadence. CVE-driven bumps consume security audit findings…
type-driven
Type-driven development. Use when developing with refined types, state machines encoded in types, or proof-carrying types; enforces totality and exhaustive pattern matching.
design-by-contract
Design-by-Contract (DbC) development. Use when implementing with formal preconditions, postconditions, and invariants across any language.