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 skills add TenWalk/ieee-skills --skill ieee-experimentsgit clone --depth 1 https://github.com/TenWalk/ieee-skillsWrote 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/tenwalk/ieee-skills/ieee-experiments)<a href="https://agentmods.dev/skills/tenwalk/ieee-skills/ieee-experiments"><img src="https://agentmods.dev/badge/skills/tenwalk/ieee-skills/ieee-experiments/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tenwalk/ieee-skills/ieee-experiments"><img src="https://agentmods.dev/badge/skills/tenwalk/ieee-skills/ieee-experiments.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00137 | $0.01431 |
| Opus 5 | $0.00068 | $0.00715 |
| Sonnet 5 | $0.00027 | $0.00286 |
| Haiku 4.5 | $0.00014 | $0.00143 |
Grade A, and why
ieee-experiments 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 10d 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.
IEEE Communications — Simulation and Numerical Results
Use this skill to make the evidence earn the claims in a PHY/network communications paper. Every contribution in the Introduction must have a result that could falsify it; for analytical papers, every derived expression must be validated by Monte-Carlo simulation; every figure answers one question.
Core stance
- Results test claims, not showcase wins. Map each contribution to the curve/table that supports it before running anything.
- Validate analysis with simulation. If the paper derives a closed-form expression (outage, BER, rate, coverage), Monte-Carlo markers must sit on the analytical curve — that agreement is the proof the derivation is correct. Note asymptotic slope (diversity order) where claimed.
- Fairness is declared, not assumed. State the comparison's boundary: same power budget, same CSI assumption, same bandwidth/antennas, same channel realizations across schemes.
- No fabrication. Do not invent curves, gains, benchmark numbers, or "matching" between theory
and simulation. Use
[PLACEHOLDER]for results not yet run and list what the user must produce.
When to open extra files
| File | Open when |
|---|---|
| references/experiment-design.md | Choosing the system/channel setup, benchmark schemes, communications metrics, Monte-Carlo protocol, convergence/complexity, learning-based evaluation (NMSE/generalization/inference cost), ISAC dual metrics (CRB/detection + rate–CRB tradeoff), and robustness (imperfect CSI/hardware) tests |
| references/tables-and-claims.md | Structuring result tables, mapping each table/figure to a claim, table/prose division of labour, and IEEE table conventions |
The evidence ladder (design in this order)
1. Validation do Monte-Carlo markers match the analysis (curves), and is the
asymptotic slope (diversity order / DoF) as claimed? [analytical papers]
2. Performance does the scheme beat conventional and prior-art schemes on the key
metric (sum rate, BER, outage, EE, ...)?
3. Operating regimes behaviour swept across SNR, #antennas, #users, power, blocklength, K-factor
4. Design analysis is each design choice necessary (compare reduced "w/o" variants)?
5. Convergence & cost does the iterative algorithm converge; complexity order vs benchmarks
6. Robustness graceful degradation under imperfect CSI, hardware impairments, mismatch
What ships with it
3 files 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.
- 10d ago First seen · 99 lines · 137 tokens per session scan A 57d3846448e6
ieee-experiments is a skill published in the GitHub repository TenWalk/ieee-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 137 tokens to every session and 1,431 once invoked, about $0.0007 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
test-first-bugs
Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.
tdd-workflow
A test-first development workflow, commonly called TDD, where a failing test is written before the code that should make it pass. The cycle then adds the smallest working change and cleans it up.
adversarial-empirical-review
N-round adversarial review pipeline for empirical research output — the chain from data to LaTeX tables to a manuscript that cites them. A Claude drafter proposes minimal diffs, a deterministic mechanical battery gates every diff from a clean state with a regression gate, a Codex reviewer files check-backed critiques…
execute
Dispatch and execute implementation plans with TDD and checkpoints. Use when plan is ready. Parallel by default for independent tasks.
tdd
Strict test-driven development for behavior changes. Requires verified RED before production code, minimal GREEN, and refactor only after passing tests.
firebase-development-add-feature
This skill should be used when adding features to existing Firebase projects. Triggers on "add function", "create endpoint", "new tool", "add api", "new collection", "implement", "build feature". Guides TDD workflow with test-first development, security rules, and emulator verification.