next-role: Skill for Claude Code

.agents/skills/upgrade-backend-deps/SKILL.md

upgrade-backend-deps is a skill for Claude Code, Codex from tam159/next-role. It costs 161 tokens per session (3,853 once invoked), scanned A, original, MIT.

A workflow for upgrading Python packages used by a backend application to the newest versions allowed by its dependency rules. It updates the lockfile, environment, tracked version pins, and optionally the backend Docker image.

In plain words
What is it for?
Refreshing backend dependencies with uv, syncing the virtual environment, updating compatible version pins, updating the Ruff pre-commit version, running unit tests, and optionally rebuilding Docker.
Why use it?
It brings dependencies up to date while keeping configuration and the installed environment aligned. Running tests helps detect problems caused by the upgrades.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is tam159/next-role's own configuration. It tells Claude Code and Codex how to work on next-role itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything next-role configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tam159/next-role. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tam159/next-role/main/.agents/skills/upgrade-backend-deps/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tam159/next-role

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for upgrade-backend-deps

README.md
[![agentmods](https://agentmods.dev/badge/skills/tam159/next-role/upgrade-backend-deps/github.svg)](https://agentmods.dev/skills/tam159/next-role/upgrade-backend-deps)
Your own site
<a href="https://agentmods.dev/skills/tam159/next-role/upgrade-backend-deps"><img src="https://agentmods.dev/badge/skills/tam159/next-role/upgrade-backend-deps/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.

agentmods 80×15 button for upgrade-backend-deps

Your own site · 80×15
<a href="https://agentmods.dev/skills/tam159/next-role/upgrade-backend-deps"><img src="https://agentmods.dev/badge/skills/tam159/next-role/upgrade-backend-deps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 161 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,853 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00161 $0.03853
Opus 5 $0.00081 $0.01927
Sonnet 5 $0.00032 $0.00771
Haiku 4.5 $0.00016 $0.00385

Measured 5d ago against content hash 8750c1fccbfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

upgrade-backend-deps 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 5d 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.

.agents/skills/upgrade-backend-deps/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upgrade the backend's Python dependencies, reconcile the version pins in tracked config, and (optionally) rebuild the Docker image so the running container picks up the new versions.

Workflow

1. Resolve and sync

cd backend
uv lock --upgrade 2>&1 | tee /tmp/uv-upgrade.log
uv sync

uv lock --upgrade re-resolves every dep against PyPI within the constraint set in pyproject.toml. Its stdout lists every Updated <pkg> vX -> vY line — that diff is the source of truth for steps 2, 3, 5, and 11. Keep it.

If the log shows Resolved N packages with no Updated lines, also check whether the lockfile itself changed:

git diff --stat backend/uv.lock
  • No diff at all → truly up to date. Stop and report "already up to date."
  • Diff exists but only inside [package.metadata] requires-dist → no packages moved, but pyproject.toml was edited out-of-band since the last lock and the metadata block just got re-synced. Skip steps 2–8 (nothing to bump, test, or rebuild — step 4's reconcile already happened as part of this --upgrade run, and no installed versions changed) and jump to step 9 to lint, then step 10 to commit/open a PR (the reconciled uv.lock still needs to land), then step 11 to report.
  • Diff includes version = "..." lines → real version moves; continue with steps 2 onward.

2. Bump pins in backend/pyproject.toml

For each package that appears in [project.dependencies] or [dependency-groups].dev, update its >=X.Y.Z lower bound to match the new locked version.

Do not bump transitive dependencies (boto3, botocore, urllib3, idna, requests, pydantic-core, etc.) — they're not in pyproject.toml at all; they're pulled in by direct deps and pinned in uv.lock. Only touch lines that already exist in the toml.

If a direct dep didn't move (e.g. held back by another constraint), leave its pin alone.

Server compat pins are not staleness. The block under # --- Agent server runtime --- in [project.dependencies] carries upper bounds (grpcio<1.81, protobuf<7, sse-starlette<3.4, jsonschema-rs<0.45, structlog<26, langgraph<2, langchain-protocol<0.1) that encode compatibility requirements of the server packages (see backend/ARCHITECTURE.md §10). Never delete or raise these ceilings as part of a routine bump — the grpcio band in particular must match the generated proto stubs, and langchain-protocol must move in lockstep with the frontend's @langchain/langgraph-sdk. If an upgrade is blocked by one of them, report it as "held by a server compat pin" rather than forcing it.

Read the full file on GitHub · 203 lines

Changes

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.

  1. 5d ago Changed · +45 lines · +10 tokens per session 8750c1fccbfc
  2. 11d ago First seen · 158 lines · 151 tokens per session scan A 9c410862925a

Subscribe to this mod's changes

upgrade-backend-deps is a skill published in the GitHub repository tam159/next-role (50 stars, last pushed 2d ago), licensed MIT. It adds 161 tokens to every session and 3,853 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

ai-dev-jobs-mcp-v2

AI Dev Jobs MCP workflow skill. Use this skill when the user needs Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP and the operator should preserve the upstream workflow, copied support files, and provenance before…

diegosouzapw/awesome-omni-skills · 78 tokens

ai-dev-jobs-mcp

AI Dev Jobs MCP workflow skill. Use this skill when the user needs Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP and the operator should preserve the upstream workflow, copied support files, and provenance before…

diegosouzapw/awesome-omni-skills · 76 tokens

openspec-verify-change

Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.

Fission-AI/OpenSpec · 32 tokens

schema-exploration

Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.

langchain-ai/deepagents · 57 tokens

omni-mcp

Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.

diegosouzapw/OmniRoute · 48 tokens

openspec-new-change

Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.

Fission-AI/OpenSpec · 40 tokens