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 jeremylongworth-source/AgentSkills --skill before-after-evaluationgit clone --depth 1 https://github.com/jeremylongworth-source/AgentSkillsWrote 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/jeremylongworth-source/agentskills/before-after-evaluation)<a href="https://agentmods.dev/skills/jeremylongworth-source/agentskills/before-after-evaluation"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/before-after-evaluation/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/jeremylongworth-source/agentskills/before-after-evaluation"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/before-after-evaluation.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 | $0.00048 | $0.00314 |
| Opus 5.5 | $0.00019 | $0.00126 |
| Sonnet 5.5 | $0.00010 | $0.00063 |
| Haiku 4.5 | $0.00005 | $0.00031 |
Grade A, and why
before-after-evaluation 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.
What it actually says
Before/After Evaluation
Core Workflow
- Confirm the scenario, target artifact, acceptance criteria, and compared conditions.
- Summarize the baseline output and the skill-enabled output using the same criteria.
- Score improvements and regressions with the project rubric.
- Separate missing context from skill failure.
- Record safety issues, reviewer edits, validation evidence, and overhead.
- Recommend keep, revise, split, merge, defer, or retire.
Safety Rules
- Do not hide regressions or unsafe assumptions because the skill helped other criteria.
- Do not publish private prompts, customer data, or sensitive outputs in public reports.
- Do not claim a skill works broadly from one easy scenario.
- Require human review for high-risk domains and production-impacting outputs.
Deliverable Shape
For before/after reports, provide:
- Scenario and target artifact
- Baseline result summary
- Skill-enabled result summary
- Rubric scores
- Improvements and regressions
- Safety and evidence notes
- Overhead notes
- Promotion decision and follow-up changes
References
- Read
references/before-after-evaluation-checklist.mdwhen preparing a before/after skill evaluation.
What ships with it
2 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.
- 1mo ago First seen · 46 lines · 48 tokens per session scan A b316b0b9490f
before-after-evaluation is a skill published in the GitHub repository jeremylongworth-source/AgentSkills (1 stars, last pushed 17d ago), licensed MIT. It adds 48 tokens to every session and 314 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 2026-08-31.
Other skills, from other repositories
idd-spec-audit
Semantic audit of the IDD instruction corpus for leaked session context, cross-file contradictions, fresh-memory completability gaps, automation blockers, and restatement-discipline drift. Use on request to audit .github/instructions, the issue-authoring skill bundle, and the installed agent entry files (CLAUDE.md…
unity-yaml-format
Inspect, explain, diff, and carefully edit Unity text-serialized files such as .unity, .prefab, .asset, and related YAML-based project files. Use when mapping class IDs and fileIDs, tracing object references, reviewing merge conflicts, or making minimal safe edits to existing UnityYAML documents.
authos-rbac-control
Manage AuthOS organization members, roles, invitations, SCIM tokens, and capability-based permissions. Use when implementing team administration, custom roles, service access grants, invitation flows, SCIM provisioning, or authorization checks inside an AuthOS tenant.
authos-service-management
Manage AuthOS tenant services, OAuth client credentials, redirect URIs, device activation URIs, plans, API keys, SAML settings, and checkout. Use when creating or configuring applications inside an AuthOS organization.
authos-platform-deployment
Deploy and configure an AuthOS API instance from source or Docker. Use when setting database backend, JWT signing keys, environment variables, billing provider, SMTP, GeoIP, Docker images, health checks, or production reverse proxy settings.
tester
Run end-to-end web quality audits with Playwright and Lighthouse using existing project scripts first. Use when the user says /tester, e2e test, smoke test, Playwright audit, Lighthouse audit, performance audit, accessibility audit, dark mode audit, mobile audit, or asks for 100/100 Lighthouse improvement guidance.