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/tlaplus/agentskills/tlaplus-split-actionnpx skills add tlaplus/AgentSkills --skill tlaplus-split-actiongit clone --depth 1 https://github.com/tlaplus/AgentSkillsWhat 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 | $0.00081 | $0.02744 |
| Opus 5 | $0.00041 | $0.01372 |
| Sonnet 5 | $0.00016 | $0.00549 |
| Haiku 4.5 | $0.00008 | $0.00274 |
Grade A, and why
tlaplus-split-action 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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Split TLA+ Action into Two Actions
Split an existing TLA+ action into two sequential actions by introducing a new intermediate pc state. This is useful for modeling finer-grained atomicity or adding intermediate steps to an action sequence.
Prerequisites
- The specification must have a
pcvariable (or equivalent likestate,phase) that tracks action sequencing. If not, create one. - The action to split must update
pcto transition between states
Overview
Given an action like:
ActionX_1(thread) ==
/\ pc[thread] = PC_ActionX_1
/\ pc' = [pc EXCEPT ![thread] = PC_Start]
/\ y' = y + 2
/\ UNCHANGED <<x, z>>
Splitting it creates:
ActionX_1(thread) ==
/\ pc[thread] = PC_ActionX_1
/\ pc' = [pc EXCEPT ![thread] = PC_ActionX_2] \* Leads to new intermediate state
/\ y' = y + 2 \* Original logic (or subset per user)
/\ UNCHANGED <<x, z>>
ActionX_2(thread) == \* New action
/\ pc[thread] = PC_ActionX_2
/\ pc' = [pc EXCEPT ![thread] = PC_Start] \* Original destination
/\ UNCHANGED <<x, y, z>> \* All vars unchanged (or subset per user)
Workflow
Step 0: Add pc variable if not present
If the specification lacks a pc variable, first use the "tlaplus-add-variable" skill to add pc variable. If the actions are thread- or process-specific, pc variable must be a function of the thread or process identifier to a string constant. For example,
PC_Begin == "PC_Begin"
PC_ActionX_1 == "PC_ActionX_1"
...
Init ==
/\ pc = [thread \in Threads |-> PC_Begin]
/\ ...
Step 1: Analyze the Target Action
Read the specification and identify:
- The action to split
- Its current
pcguard (entry state) - Its
pc'assignment (exit state) - All variable updates in the action
- The UNCHANGED statement
- The naming convention used (numbered suffix like
_0,_1, etc.)
Step 2: Determine the New PC State Name
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 · 323 lines · 81 tokens per session scan A 2b2eebee8e75
tlaplus-split-action is a skill published in the GitHub repository tlaplus/AgentSkills (36 stars, last pushed 7mo ago), licensed MIT. It adds 81 tokens to every session and 2,744 once invoked, about $0.0004 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
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.