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/mrmps/chomsky-stack/meaningful-contributionnpx skills add mrmps/chomsky-stack --skill meaningful-contributiongit clone --depth 1 https://github.com/mrmps/chomsky-stackWhat 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 | $0.00079 | $0.00963 |
| Opus 5 | $0.00039 | $0.00481 |
| Sonnet 5 | $0.00016 | $0.00193 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
meaningful-contribution 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meaningful Contribution
Treat the deliverable as a change plus credible evidence that it works. Match the depth of proof to the change's risk, and never claim checks that were not run.
Establish the proof contract
Before editing:
- State the user-visible or system-visible behavior that must change.
- Identify the narrowest way to observe that behavior.
- List the important failure modes and non-happy paths.
- Find the repository's own instructions and existing test patterns.
- Choose the evidence required for completion.
For a bug fix, reproduce the failure before changing code whenever feasible. For a feature, define concrete acceptance examples. For a refactor, define the behavior and interfaces that must remain unchanged.
Build the smallest coherent change
- Prefer the smallest change that fully satisfies the proof contract.
- Keep names, types, and abstractions truthful. A name is a contract; rename or redesign anything that requires “it says X, but really means Y” to understand it.
- State expected inputs, outputs, state transitions, and behavior for invalid or unexpected inputs.
- Fit the repository's established domain model and patterns. Do not introduce a competing abstraction without a clear need.
- Read every changed line in context after generation. Remove accidental complexity, dead branches, broad casts, and unrelated cleanup.
Prove behavior in layers
Use the applicable layers below. Do not substitute static inspection for runtime evidence when runtime behavior changed.
1. Observe it directly
Exercise the changed path manually or through the smallest representative command. Confirm the actual output, UI state, side effect, or failure behavior.
For UI work, inspect each affected viewport and interaction state. For APIs or jobs, exercise realistic input and inspect the response plus relevant persisted or emitted state.
2. Add automated regression coverage
Encode the observed behavior in the narrowest stable test that would catch a regression. Prefer behavior assertions over implementation details.
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 · 99 lines · 79 tokens per session scan A 349fe5ae7d12
meaningful-contribution is a skill published in the GitHub repository mrmps/chomsky-stack (7 stars, last pushed 4d ago), licensed MIT. It adds 79 tokens to every session and 963 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 2026-08-31.
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…