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/jakkaj/tools/thesisnpx skills add jakkaj/tools --skill thesisgit clone --depth 1 https://github.com/jakkaj/toolsWhat 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 | $0.00069 | $0.00540 |
| Opus 5 | $0.00034 | $0.00270 |
| Sonnet 5 | $0.00014 | $0.00108 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
thesis 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.
What it actually says
Thesis
Understand the work before doing the work. Flow-blind and read-only.
Modes
ask <request> — what the work should become.
thing <target> — what the existing thing is and serves.
fit <target> to <request> — where it is, where it must go, and what must
survive.
No mode: ask only → ask; target only → thing; both → fit. Never infer
from workflow position alone.
Method
- Read the ask or target and only its nearest authoritative context.
- Derive Thesis (purpose/promise), Now (position), Toward (outcome or next consumer), and Keep (vibe, invariant, tension, or anti-goal).
- Mark inference plainly; invent no missing intent.
- Keep only ideas that should steer more than one later decision.
- Stop before planning, critique, edits, or execution.
Output
Emit only the axes that apply (2–4 of them), each as its own paragraph separated by a blank line, one sentence each, the label in bold followed by an em dash:
**Thesis** — <governing idea and promise>
**Now** — <current position or starting truth>
**Toward** — <destination or consumer need>
**Keep** — <character, invariant, tension, or anti-goal>
Then a blank line and a blockquote synthesis — one paragraph of at most three sentences that ties the axes together and shows what "right" should feel like:
> **My read:** <synthesis>
Formatting adds air, not words. The blank lines, bold labels, and blockquote exist to make the same short read scannable — never to invite more content. Hold to 2–4 axis lines and a ≤3-sentence synthesis.
No heading, praise, recap, plan, checklist, critique, or work. Do not repeat the axes in prose. If ambiguity would materially change the read, ask one question instead of inventing. The output must stand alone when returned from a subagent.
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 · 65 lines · 69 tokens per session scan A 86e50e802a4b
thesis is a skill published in the GitHub repository jakkaj/tools (5 stars, last pushed 17d ago), licensed MIT. It adds 69 tokens to every session and 540 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.
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…