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 reidemeister94/development-skills --skill eval-regressiongit clone --depth 1 https://github.com/reidemeister94/development-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/reidemeister94/development-skills/eval-regression)<a href="https://agentmods.dev/skills/reidemeister94/development-skills/eval-regression"><img src="https://agentmods.dev/badge/skills/reidemeister94/development-skills/eval-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/reidemeister94/development-skills/eval-regression"><img src="https://agentmods.dev/badge/skills/reidemeister94/development-skills/eval-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 | $0.00023 | $0.00513 |
| Opus 5.5 | $0.00009 | $0.00205 |
| Sonnet 5.5 | $0.00005 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
eval-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 1mo 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval regression
Use deterministic repository tests first. Stop when the target has no behavioral diff.
Resolve the plugin from the argument or cwd. Its catalog is evals/evals.json; the runner is scripts/run_evals.py in this skill.
Require the user to choose agent, model, and effort. Never select a costly model or high effort silently.
Normal check
- Select cases by changed paths with
--changed-from <base>, or name them with--case. Do not select the full catalog implicitly. - Run the command without
--run. The runner prints cases, modes, repeats, sessions, timeout, and maximum duration without starting an agent. - An approved plan that names this exact run already authorizes it. For a standalone eval, present the run plan and stop once.
- After approval, repeat the same command with
--run. Default to candidate-only, one run per case, 180 seconds, and four sessions maximum. - Report every failed assertion, timeout, non-zero exit, duration, and token count. Missing evidence is inconclusive.
Escalation
- Compare base and candidate only when the user asks, or when a failed candidate check needs a baseline.
- Extract the base with
git archive. Use the same cases, agent, model, effort, repeats, and timeout on both versions. - Repeat only a failed or observably unstable case. Three repeats are a stability benchmark, not a default.
--all,--repeat > 1, more sessions, or a longer timeout is new scope. Update the run plan and get authority first.- Routing cases stop at the first Skill selection. Tool assertions are appropriate because routing is the contract.
Remove temporary base copies after the comparison. Do not edit or commit the target.
Deterministic assertions are tool, tool_not, clean_worktree, changed_files_exact, file_contains, file_not_contains, transcript_contains, and tool_sequence.
Use a semantic judge only when no filesystem, command, tool, ordering, or assistant-output observation can express the contract.
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.
- 1mo ago Changed · +3 lines · -8 tokens per session 9673f8120b24
- 1mo ago First seen · 32 lines · 31 tokens per session scan A 7ba5eb7c74c5
eval-regression is a skill published in the GitHub repository reidemeister94/development-skills (12 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 513 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
mutation-test
Mutation testing with two engines. Uses the project's NATIVE mutation runner (StrykerJS / Infection / mutmut / PIT / cargo-mutants) when one is configured — installing it on explicit consent when it is not — for a reproducible, comparable score; and an LLM-guided engine for the mutation classes native mutators cannot…
write-tests
Write tests for existing production code. Processes ONE file at a time through a full pipeline: analyze, inventory (frozen BEFORE writing), write, executable coverage gate, verify, blind coverage audit, adversarial review, log. Uses CodeSift for discovery and analysis when available. Modes: [path] (specific target)…
code-audit
Batch audit of production files against CQ1-CQ40 quality gates and CAP1-CAP29 anti-patterns. Tiered output (A/B/C/D), critical gate enforcement, evidence-backed scoring, cross-file pattern analysis, and prioritized execution plan. Flags: zuvo:code-audit all | [path] | [file] | --deep | --quick | --services |…
plan
Analyzes architecture, selects patterns, assesses testability, then decomposes work into ordered TDD tasks with exact verification commands and explicit acceptance mapping. Works from an approved spec (zuvo:brainstorm output) or directly from a user-provided description.
pentest
Hybrid white-box + black-box penetration testing across 7 dimensions (PT1-PT7). Stack-aware source-to-sink tracing, exploit verification, CMS overlay, and deterministic finding aggregation. Uses explicit candidate schemas, canonical-key deduplication, score caps, and MUST-GATE enforcement. Flags: zuvo:pentest [path] |…
api-audit
API and endpoint integrity audit across 10 dimensions (D1-D10) plus optional contract stability (D11) and optional OWASP API Security Top 10 (D12: BOLA/BOPLA/BFLA, mass assignment, JWT alg-confusion, GraphQL introspection). Covers validation, payloads, pagination, errors, caching, HTTP semantics, waterfalls, rate…