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 hamzabellouch/agent-skills --skill information-theory-and-codinggit clone --depth 1 https://github.com/hamzabellouch/agent-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/hamzabellouch/agent-skills/information-theory-and-coding)<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/information-theory-and-coding"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/information-theory-and-coding/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/hamzabellouch/agent-skills/information-theory-and-coding"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/information-theory-and-coding.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 | $0.00060 | $0.00432 |
| Opus 5.5 | $0.00024 | $0.00173 |
| Sonnet 5.5 | $0.00012 | $0.00086 |
| Haiku 4.5 | $0.00006 | $0.00043 |
Grade A, and why
information-theory-and-coding 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 today.
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
Information Theory & Coding
- Entropy H(X) = -sum p log2 p (bits); max log2 n for uniform; H(X,Y) = H(X) + H(Y|X); conditional entropy; chain rule.
- Mutual information I(X;Y) = H(X) - H(X|Y) >= 0; data-processing inequality; KL divergence D(p||q) = sum p log(p/q) >= 0 (Gibbs); cross-entropy loss in ML = H(p) + D(p||q).
- Source coding theorem: average code length >= H; Huffman optimal prefix code; Kraft inequality sum 2^{-l_i} <= 1; arithmetic coding; Lempel-Ziv universal compression.
- Channel capacity C = max I(X;Y); binary symmetric channel C = 1 - H(p); AWGN (Shannon-Hartley) C = B log2(1 + S/N); noisy-channel coding theorem (rates below capacity achievable with vanishing error).
- Error-correcting codes: Hamming distance, Hamming(7,4) corrects 1 error, parity checks; linear codes (generator/parity-check matrices, syndrome); Reed-Solomon (CDs, QR codes), BCH, LDPC and turbo codes (near capacity), polar codes; Singleton, Hamming, Gilbert-Varshamov bounds.
- Rate-distortion theory, lossy compression (JPEG, MP3 transforms).
- Kolmogorov complexity (uncomputable), minimum description length, maximum entropy principle; connections to statistical mechanics (Boltzmann = Shannon up to k_B ln 2) and quantum information (von Neumann entropy).
- Password strength: entropy bits = length x log2(alphabet size) if random.
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.
- today First seen · 16 lines · 60 tokens per session scan A fcd19d5a0db1
information-theory-and-coding is a skill published in the GitHub repository hamzabellouch/agent-skills (8 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 432 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-17.
Other skills, from other repositories
polya-docs
Phase 6 of the Pólya Heuristic Coder: Technical Documentation via Diátaxis Framework (Tutorials, How-To Guides, Reference, Explanation).
agricultural-sciences-professor
Use when a task needs the judgment of a tenure-track or tenured Agricultural Sciences faculty member at a land-grant university — deciding whether to submit a grant this cycle versus wait, allocating time across the teaching/research/extension appointment split, diagnosing a stalled graduate student or field trial, or…
adapted-physical-education-specialist
Use when a task needs the judgment of an Adapted Physical Education Specialist — writing a legally-defensible PE present level and annual goal from motor/fitness assessment data, choosing the right test battery and alternate items for a student's mobility profile, recommending a placement step on the PE…
area-ethnic-cultural-studies-professor
Use when a task needs the judgment of an Area, Ethnic, or Cultural Studies Professor — designing a joint-appointment course load across two departments, prepping a tenure or mid-tenure review file for interdisciplinary scholarship, deciding whether a course survives an enrollment or political-pressure threat…
art-drama-music-professor-postsecondary
Use when a task needs the judgment of a Postsecondary Art, Drama, or Music Professor — diagnosing a jury/crit score that contradicts a semester of formative work, building a studio-art or performance tenure dossier around exhibitions and productions instead of publications, staffing applied one-on-one lessons or crit…
career-technical-education-teacher-postsecondary
Use when a task needs the judgment of a Career/Technical Education Teacher, Postsecondary — defending a shrinking trade or health-science program against a cutback decision, backward-mapping a shop or lab curriculum to an industry credential's exam blueprint, resolving a competency-based grading dispute where a…