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/outline-driven-development --skill deps-upgradegit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outline-driven-development/deps-upgrade)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/deps-upgrade"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/deps-upgrade/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/deps-upgrade"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/deps-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.02542 |
| Opus 5 | $0.00022 | $0.01271 |
| Sonnet 5 | $0.00009 | $0.00508 |
| Haiku 4.5 | $0.00004 | $0.00254 |
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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deps upgrade
Contract
| Field | Bound contract |
|---|---|
| Trigger | CVE remediation, major upstream release, compatibility-forced sweep, scheduled dependency hygiene, pre-release lockfile audit, or a cadence-driven or vulnerability-triggered dependency sweep. |
| Authority | Reversible local: writes only manifests, lockfiles, and compatibility code in the current repository (concern-atomic local commits) plus a temporary lockfile snapshot outside the tree for the pre/post audit; rollback is version control (revert the campaign commits or reset to the recorded pre-campaign HEAD). No remote mutation. |
| Side effect | Updates local manifests, lockfiles, and compatibility code; creates concern-atomic local commits. No feature work, no refactors beyond compatibility code, no silent lockfile drift. |
| Done | Selected upgrades are locked, tested at the required depth, migration guidance applied for majors, license/SBOM churn checked, and the final vulnerability scan is recorded. For a sweep, each update is classified on the risk ladder and verified, or deferred with a recorded reason. |
Inputs
Must be supplied: a working repository with VCS history; toolchains for each in-scope ecosystem; and operator scope directives: which ecosystems and paths are in scope, the highest tier allowed (patch, minor, or major), and any package allowlist/blocklist. Optional: pinned target versions for specific majors, a CVE scanner choice (defaults to the ecosystem canonical scanner below), a vulnerability report or advisory feed naming affected dependencies, a cadence schedule, and freeze-window or deadline constraints that cap the tier ceiling. A major bump requires explicit human approval supplied at runtime. Before the first mutation, verify each required tool exists (command -v) and run the full test suite on the clean tree as the baseline; missing tools or a red baseline stop the run before anything changes.
Procedure
- Gate (no mutation yet): stop without changing anything if any holds: active feature branch with high churn; pre-release freeze window; mid-incident; the task is an API-break-driven refactor rather than a dependency upgrade. Report which gate tripped. Done when: all gates pass or the tripped gate is reported without mutation.
- Bound scope: fix from the operator directives the ecosystem list, path scope, tier ceiling, and allowlist/blocklist. Never widen during the run; findings outside scope become report items, not work. Done when: all scope fields are frozen.
- Baseline: record the pre-campaign HEAD sha and snapshot every lockfile to a temporary directory; this snapshot is the audit baseline and the rollback anchor. Done when: the HEAD and every lockfile snapshot are recorded.
- Inventory: enumerate manifests and lockfiles across the in-scope ecosystems. Canonical names are often extensionless (
go.mod,Gemfile,pom.xml), so filter on filenames, not extensions;fdtakes one glob per call, so anchor on canonical filenames with one regex:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed · -34 tokens per session 61425b2fb7f8
- 5d ago First seen · 81 lines · 78 tokens per session scan A f60982023cc9
deps-upgrade is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 44 tokens to every session and 2,542 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
snippet-image-rendering
Use when the user explicitly names snipgrapher and wants code rendered to a polished PNG, SVG, or WebP at an explicit local path. Probes the installed CLI for supported flags and writes only the named image file. Not for other renderers, publishing, or remote actions.