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/adr-authornpx skills add evolplus/talos --skill adr-authorgit clone --depth 1 https://github.com/evolplus/talosWrote 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/evolplus/talos/adr-author)<a href="https://agentmods.dev/skills/evolplus/talos/adr-author"><img src="https://agentmods.dev/badge/skills/evolplus/talos/adr-author.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 | $0.00048 | $0.01401 |
| Opus 5 | $0.00024 | $0.00700 |
| Sonnet 5 | $0.00010 | $0.00280 |
| Haiku 4.5 | $0.00005 | $0.00140 |
Grade A, and why
adr-author 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR Author
When to use
You are the SA, drafting docs/architecture.md or revising it during change synchronization. You face a choice that would surprise a new engineer joining the project, or that involves a trade-off you'd want a successor to understand. Per CLAUDE.md §3.2: every non-trivial choice gets an ADR. This skill defines the format and the trigger.
Inputs and outputs
- Inputs: a candidate architectural choice and the alternatives you're weighing
- Outputs: a numbered ADR file under
docs/decisions/, in the format inreferences/template.md
When a choice is "non-trivial"
A choice deserves an ADR when at least one is true:
- It's a one-way door (hard to reverse later — pricing model, data partition strategy, primary key shape)
- It commits the team to a vendor or stack (Postgres vs DynamoDB, Stripe vs Adyen, REST vs gRPC)
- It contradicts a previous default (the team usually does X; for this feature we're doing Y)
- A reasonable engineer would assume the opposite default
- It encodes a trade-off (cost vs latency, simplicity vs flexibility, build vs buy)
If a choice is "the obvious thing the team always does," no ADR. If you can't tell, write the ADR — it's cheap.
Third-party dependency ADRs (require human Approver)
When the ADR introduces a third-party dependency that has not been approved in a prior ADR for this project, the ADR gains two required fields:
Approver: <human name>— the Designated Dependency Approver named in SRS header per CLAUDE.md §2. Set by the user through the Orchestrator'sNEEDS_CONTEXTclarification flow; never set by the agent.Approval-Date: <ISO-8601>— the date the human approved the choice.
Per CLAUDE.md §10 hard rule, you must NOT write the ADR with Status: Accepted until the human has approved. The flow:
- While drafting architecture, you identify a needed third-party dependency.
- Use
.claude/skills/third-party-dependency-evaluation/SKILL.mdto evaluate options. - Halt and return
NEEDS_CONTEXTto the Orchestrator with the multi-choice proposal. - The Orchestrator relays to the Designated Dependency Approver.
- The Approver picks an option.
- Resume work. Write the ADR with
Status: Accepted,Approver: <name>,Approval-Date: <date>.
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 First seen · 92 lines · 48 tokens per session scan A ab923d99e36d
adr-author is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 29d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,401 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…