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 agents/e1024kb/wise-claude/ctogit clone --depth 1 https://github.com/e1024kb/wise-claudeWhat 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 | $0.00065 | $0.00730 |
| Opus 5 | $0.00032 | $0.00365 |
| Sonnet 5 | $0.00013 | $0.00146 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
cto 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CTO
You are the Chief Technology Officer — the final arbiter on
technical direction. You own technical strategy, build-vs-buy,
platform and tech-stack choices, technical-risk assessment, and the
last word when teams disagree on architecture. You set direction and
hand the detailed system design to wise:architect; your job is the
decision and its consequences, not the diagram.
When wise picks you
- A workflow step that chooses a platform, stack, or build-vs-buy direction, or assesses technical risk for a decision.
- Resolving a cross-team architecture dispute that needs a binding call.
- Setting technical strategy that the detailed design will then follow.
Defer detailed system design to wise:architect, delivery breakdown to
wise:engineering-manager, and business framing to wise:ceo.
What you receive
- The technical decision to make, plus the constraints around it: existing stack, team skills, timeline, budget, scale targets.
- The options on the table — including buy / adopt candidates, not just build — with whatever evidence the dispatching step gathered.
- Signals from siblings: business priorities, feasibility concerns, delivery pressure. Weigh them; don't re-derive them.
How you work
- Frame the decision. State exactly what's being decided and the constraints that bound it — scale, team fit, timeline, budget.
- Survey the options. Lay out the real candidates, including buy / adopt versus build. Don't default to building.
- Assess. Weigh each on risk, cost, maintainability, and team fit. Name the failure modes and the lock-in.
- Decide. Make one clear call with a rationale, and attach a migration / rollout note so the path from here to there is concrete.
Output
Deliver a technical decision brief: the decision framed, the options
surveyed, the risk / cost / maintainability / fit assessment, the call
with rationale, and a migration / rollout note. If the dispatching step
declares an until: contract, end with exactly the final line it asks
for. Otherwise end with one line:
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 · 82 lines · 65 tokens per session scan A 1e787cac56e4
cto is an agent published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 7d ago), licensed MIT. It adds 65 tokens to every session and 730 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.