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 Vibe-Marketer/plugins-and-skills --skill compound-engineeringgit clone --depth 1 https://github.com/Vibe-Marketer/plugins-and-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/vibe-marketer/plugins-and-skills/compound-engineering)<a href="https://agentmods.dev/skills/vibe-marketer/plugins-and-skills/compound-engineering"><img src="https://agentmods.dev/badge/skills/vibe-marketer/plugins-and-skills/compound-engineering.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 5.1 | $0.00076 | $0.01796 |
| Opus 5 | $0.00038 | $0.00898 |
| Sonnet 5 | $0.00015 | $0.00359 |
| Haiku 4.5 | $0.00008 | $0.00180 |
Grade A, and why
compound-engineering 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 6d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill implements Compound Engineering—a development methodology where each unit of work makes subsequent work easier, not harder. Inspired by Every.to's engineering approach.
Core Philosophy
Each unit of engineering work should make subsequent units of work easier—not harder.
Traditional development accumulates technical debt. Every feature adds complexity. Every change increases maintenance burden. Compound engineering inverts this by creating a learning loop where each bug, failed test, or problem-solving insight gets documented and used by future work.
The Compound Engineering Loop
Plan → Work → Review → Compound → (repeat)
- Plan (40%): Research approaches, synthesize information into detailed implementation plans
- Work (20%): Execute the plan systematically with continuous validation
- Review (20%): Evaluate output quality and identify learnings
- Compound (20%): Feed results back into the system to make the next loop better
80% of compound engineering is in planning and review. 20% is in execution.
Step 1: Plan
Before writing any code, create a comprehensive plan. Good plans start with research:
Research Phase
- Codebase Analysis: Search for similar patterns, conventions, and prior art in the codebase
- Commit History: Use
git logto understand how related features were built - Documentation: Check README, AGENTS.md, and inline documentation
- External Research: Search for best practices relevant to the problem
Plan Document Structure
Create a plan document (markdown) with:
# Feature: [Name]
## Context
- What problem does this solve?
- Who is affected?
- What's the current behavior vs desired behavior?
## Research Findings
- Similar patterns found in codebase: [list with file links]
- Relevant prior implementations: [commit references]
- Best practices discovered: [external references]
## Acceptance Criteria
- [ ] Criterion 1 (testable)
- [ ] Criterion 2 (testable)
- [ ] Criterion 3 (testable)
## Technical Approach
1. Step 1: [specific action]
2. Step 2: [specific action]
3. Step 3: [specific action]
## Code Examples
[Include code snippets that follow existing patterns]
## Testing Strategy
- Unit tests: [what to test]
- Integration tests: [what to test]
- Manual verification: [steps]
## Risks & Mitigations
- Risk 1: [mitigation]
- Risk 2: [mitigation]
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.
- 6d ago First seen · 251 lines · 76 tokens per session scan A b1bb1a24c7dd
compound-engineering is a skill published in the GitHub repository Vibe-Marketer/plugins-and-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 76 tokens to every session and 1,796 once invoked, about $0.0004 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.