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/ddddjaak/se-skills/algorithm-designnpx skills add ddddjaak/se-skills --skill algorithm-designgit clone --depth 1 https://github.com/ddddjaak/se-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/ddddjaak/se-skills/algorithm-design)<a href="https://agentmods.dev/skills/ddddjaak/se-skills/algorithm-design"><img src="https://agentmods.dev/badge/skills/ddddjaak/se-skills/algorithm-design.svg" alt="Measured on agentmods" 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 | $0.00119 | $0.04130 |
| Opus 5 | $0.00060 | $0.02065 |
| Sonnet 5 | $0.00024 | $0.00826 |
| Haiku 4.5 | $0.00012 | $0.00413 |
Grade A, and why
algorithm-design 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 3d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Algorithm Design
Overview
System requirements and architecture often identify modules whose behavior is inherently algorithmic: a PID temperature controller, a low-pass filter chain for sensor data, a touch calibration routine, an FFT-based fault detector. These modules cannot be specified by interface alone — you need to define the math, the parameters, the precision, the convergence guarantees.
This skill takes algorithm-relevant requirements and the system architecture as input and produces a quantified algorithm design document. It answers the "how does this module compute?" question that architecture-design leaves for the spec author. Every parameter is traced to a requirement. Every precision, latency, and memory claim is backed by a number with units. Every hardware-dependent assumption is explicit — and if the hardware spec does not yet provide the needed characteristic, the design flags it rather than guessing.
When to Use
- System requirements contain quantitative algorithmic needs (e.g., "filter settling time ≤ 10ms", "PID overshoot ≤ 5%", "calibration accuracy ±1 LSB")
- The architecture document identifies modules whose core responsibility is computation, not just data plumbing (signal processing blocks, control loops, estimation/calibration, transforms)
- A downstream skill (
spec-authoring) detects that a module in the architecture decomposition has algorithm behavior described only by the module name ("Touch Calibration Module") with no math, no parameters, no convergence criteria - Adding a new algorithm to an existing system (new sensor processing pipeline, new control strategy)
- An algorithm behavior depends on hardware characteristics that must be verified before implementation (ADC noise floor, DAC settling time, sensor response curve)
When NOT to use: The module is purely data plumbing (reads a register, writes a buffer, translates a protocol) — use architecture-design interface definitions. The algorithm is a standard library call with no design decisions (e.g., memcpy, crc32, arm_biquad_cascade_df1_f32). Algorithm requirements do not yet exist — run requirements-decompose first. The module's algorithm is already fully specified with quantified parameters traced to requirements.
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.
- 3d ago First seen · 263 lines · 119 tokens per session scan A 1c28b84659d1
algorithm-design is a skill published in the GitHub repository ddddjaak/se-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 4,130 once invoked, about $0.0006 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
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
nature-statistics
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…
evaluating-with-leakage-gates
Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.