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 Team-Deepiri/deepiri-axiom --skill symbolic-regressiongit clone --depth 1 https://github.com/Team-Deepiri/deepiri-axiomWrote 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/team-deepiri/deepiri-axiom/symbolic-regression)<a href="https://agentmods.dev/skills/team-deepiri/deepiri-axiom/symbolic-regression"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/symbolic-regression/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/team-deepiri/deepiri-axiom/symbolic-regression"><img src="https://agentmods.dev/badge/skills/team-deepiri/deepiri-axiom/symbolic-regression.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 | $0.00078 | $0.01362 |
| Opus 5.5 | $0.00031 | $0.00545 |
| Sonnet 5.5 | $0.00016 | $0.00272 |
| Haiku 4.5 | $0.00008 | $0.00136 |
Grade A, and why
symbolic-regression 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 11d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Symbolic and sparse-regression model discovery
Companion to applied-math. That skill is the disciplined, largely hand-driven process for inventing
structure; this one is the computational toolkit for when you have data dense enough that a machine
search over candidate equations can propose structure faster than hand derivation — with the same
non-negotiable requirement that every proposal gets run back through applied-math's validation stages
before being trusted. A computer finding a sparse fit is a hypothesis, not a result.
Choosing a technique
| Situation | Reach for |
|---|---|
| You already trust a set of state variables and want the governing equation | Sparse regression (SINDy family). Build a library of candidate terms, solve for the sparsest coefficient vector reproducing observed derivatives or transitions. |
| Derivatives are noisy or only available from finite differences | Weak/integral-form SINDy. Regress against integrated quantities instead of pointwise derivatives — far more robust to measurement noise. |
| Dynamics genuinely span multiple time scales | Multiscale sparse regression. Resample and fit fast and slow components on separate, appropriately-chosen sampling intervals rather than one global fit. |
| You don't yet trust a term library or functional form at all | Symbolic regression search (genetic-programming or search-based, e.g. PySR-style tools). Searches over expression trees rather than coefficients of a fixed basis — slower and more prone to spurious fits, but doesn't require committing to a basis first. |
| You suspect the raw measured variables aren't the right state, but have no candidate re-description | Data-driven coordinates — dynamic mode decomposition for (locally) linear systems, autoencoders or diffusion maps for nonlinear ones. Produces candidate coordinates to feed back into the state-variable search, not a final answer. |
| You want to estimate a nearly-conserved quantity or fast/slow split directly from snapshots | DMD spectrum. Eigenvalues near the unit circle (continuous case: near zero) are your candidate slow modes; the rest are fast. Ties directly into the linear-algebraic lens in applied-math. |
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.
- 11d ago First seen · 83 lines · 78 tokens per session scan A 0b38b3c593da
symbolic-regression is a skill published in the GitHub repository Team-Deepiri/deepiri-axiom (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 78 tokens to every session and 1,362 once invoked, about $0.0003 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 2026-10-26.
symbolic-regression compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| symbolic-regressionTeam-Deepiri/deepiri-axiom | Skill | 2 | yesterday | Apache-2.0 | A | 78 | Claude Code |
| arboretoK-Dense-AI/scientific-agent-skills | Skill | 56k | 5d ago | MIT | A | 55 | Claude Code, Codex |
| deepspot-mK-Dense-AI/scientific-agent-skills | Skill | 56k | 5d ago | MIT | A | 70 | Claude Code |
| torchdrugK-Dense-AI/scientific-agent-skills | Skill | 56k | 5d ago | MIT | A | 64 | Claude Code |
| pyhealthK-Dense-AI/scientific-agent-skills | Skill | 56k | 5d ago | MIT | A | 84 | Claude Code, Codex |
| nemo-mbridge-perf-expert-parallel-overlapNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| ml-training-recipesOrchestra-Research/AI-Research-SKILLs | Skill | 14k | 27d ago | MIT | A | 88 | Claude Code |