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/evolplus/talos/solution-defaultsnpx skills add evolplus/talos --skill solution-defaultsgit clone --depth 1 https://github.com/evolplus/talosWhat 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 | $0.00063 | $0.01576 |
| Opus 5 | $0.00032 | $0.00788 |
| Sonnet 5 | $0.00013 | $0.00315 |
| Haiku 4.5 | $0.00006 | $0.00158 |
Grade A, and why
solution-defaults 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 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.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solution Defaults
When to use
You are SA producing architecture, or a Dev about to add a dependency. Check this skill before running through .claude/skills/third-party-dependency-evaluation/. The defaults in references/defaults-table.md are pre-approved at the org level — using them skips per-project human approval. Deviating from a default, or using a category not covered, still requires the full evaluation + NEEDS_CONTEXT flow.
How defaults interact with the approval flow
SA / Dev needs a dependency
↓
Step 1 — Open references/defaults-table.md
├── Category has a default (Status: ✓) AND you'll use it
│ → Use it. Write ADR citing this skill as the approval source. No NEEDS_CONTEXT.
├── Category has a default but row is Status: ⚠ (starter, not yet confirmed)
│ → Treat as a hint, not binding. Full .claude/skills/third-party-dependency-evaluation/ flow.
├── Category has a default (Status: ✓) BUT you need to deviate
│ → Full .claude/skills/third-party-dependency-evaluation/ flow.
│ → ADR records project's Designated Dependency Approver + the deviation reason.
└── Category not in the table
→ Full .claude/skills/third-party-dependency-evaluation/ flow.
→ ADR records project's Designated Dependency Approver.
→ Consider proposing the result as a new default — see "Adding a new default" below.
Where the defaults live
The table of pre-approved defaults is in references/defaults-table.md, separated from this skill so the table can be edited and reviewed independently of the procedure.
The table has five columns:
- Category — the dependency kind (relational DB, cache, queue, etc.)
- Default — the chosen vendor / technology
- Rationale — why this default exists
- Deviate when — concrete conditions under which the default does not apply
- Status —
✓ confirmed(binding) or⚠ starter(placeholder, not yet ratified)
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.
- 2d ago First seen · 112 lines · 63 tokens per session scan A a8a984399a3f
solution-defaults is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 28d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,576 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…