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.
curl -O https://raw.githubusercontent.com/tam159/next-role/main/.agents/skills/upgrade-backend-deps/SKILL.mdgit clone --depth 1 https://github.com/tam159/next-roleWrote 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/tam159/next-role/upgrade-backend-deps)<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.
<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>- 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 | $0.00161 | $0.03853 |
| Opus 5 | $0.00081 | $0.01927 |
| Sonnet 5 | $0.00032 | $0.00771 |
| Haiku 4.5 | $0.00016 | $0.00385 |
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.
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, butpyproject.tomlwas 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--upgraderun, and no installed versions changed) and jump to step 9 to lint, then step 10 to commit/open a PR (the reconcileduv.lockstill 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.
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.
- 5d ago Changed · +45 lines · +10 tokens per session 8750c1fccbfc
- 11d ago First seen · 158 lines · 151 tokens per session scan A 9c410862925a
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.
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…
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…
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
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.
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.
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.