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 SW-in-beta/simon-skills --skill simongit clone --depth 1 https://github.com/SW-in-beta/simon-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/sw-in-beta/simon-skills/simon)<a href="https://agentmods.dev/skills/sw-in-beta/simon-skills/simon"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon/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/sw-in-beta/simon-skills/simon"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon.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 | $0.00169 | $0.09443 |
| Opus 5 | $0.00084 | $0.04722 |
| Sonnet 5 | $0.00034 | $0.01889 |
| Haiku 4.5 | $0.00017 | $0.00944 |
Grade A, and why
simon 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 8d 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 — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.
simon
Deep workflow skill with 19-step quality pipeline.
Instructions
You are executing the simon deep workflow. This is a 19-step quality pipeline that plans, implements, and verifies code with maximum rigor.
State-Driven Execution
매 턴(응답) 시작 시 반드시 실행하는 루틴 — compaction, 세션 재개, 작업 전환 후 복귀 등 어떤 상황에서도 적용된다. 이 루틴이 없으면 compaction 후 현재 위치를 잃고 이전 Step을 반복하거나 건너뛸 수 있다:
{SESSION_DIR}/memory/workflow-state.json읽기current_step에 해당하는 Phase의 reference 목록 확인 (Reference Loading Policy 테이블)references_loaded필드에 해당 reference가 없으면 → 재로딩. 있으면 → 스킵. Compaction 감지 시 Tier별 선택적 초기화 — Tier 1은 강제 재로딩, Tier 2는 현재 Phase에 해당하는 것만 재로딩, Tier 3는 초기화하지 않음 (on-demand 트리거로 자연스럽게 재로딩). "이전에 읽었으니 알고 있다"가 LLM 기억이 아닌 JSON 기록에 기반해야 핵심 규칙 소실을 방지한다. 3-B. 이전 Step 산출물 로딩 (세션 독립성 핵심):step_outputs[prev_step]에 기록된 파일들을 로딩한다.
- 새 세션 감지 시 (workflow-state.json의
session_id가 현재 Startup에서 설정한 값과 다르거나 없으면): 반드시 로딩 - 동일 세션 내: 이미 컨텍스트에 있으면 스킵
- Why: 새 세션에서 Step N을 시작할 때 Step N-1의 산출물 파일이 컨텍스트에 없으면 잘못된 판단이나 중복 작업이 발생한다.
step_outputs는 Step 완료 시 기록되므로, 이 파일들을 로딩하면 이전 Step의 결과를 즉시 복원할 수 있다.
- 해당 Step 실행
- Step 완료 즉시 workflow-state.json 갱신 (
references_loaded+step_outputs포함)
workflow-state.json이 없으면 Startup부터 시작한다.
갱신 규칙: Step 시작 시 current_step, 완료 시 completed_steps+next_step, Phase 전환 시 current_phase+phase_timestamps 갱신. 중단/에러: blocked: true. Step skip 시 skipped_steps 기록. Phase A 완료 시 Done-When Checks → done_when_checks 배열 추출 (verified: false 초기값). Step 5d/6/17 검증 통과 시 verified: true 갱신. Step 17에서 verified: false 잔존 시 FAIL — JSON boolean은 명시적 갱신이 필요하므로 LLM의 임의 체크 방지.
Step 산출물 추적 (세션 독립성): Step 완료 시 step_outputs[step_id]에 해당 Step이 생성한 핵심 파일의 경로 목록(SESSION_DIR 기준 상대 경로)을 기록한다. 이 목록이 다음 세션의 진입점이 된다 — 새 세션에서 Step N을 시작할 때 step_outputs[prev_step]을 읽으면 이전 Step의 산출물을 즉시 로딩할 수 있다. Startup 시 session_id를 ISO-8601 타임스탬프로 기록하여, 새 세션과 compaction 복구를 구분한다.
{
"current_step": "B/7",
"session_id": "2026-04-14T10:30:00+09:00",
"step_outputs": {
"A/0": ["memory/codebase-health.md", "memory/plan-summary.md"],
"A/1-A": ["memory/requirements.md", "memory/code-design-analysis.md", "memory/verify-commands.md", "memory/env-context.md"],
"A/1-B": ["memory/plan-summary.md"],
"A/2-4": ["memory/plan-summary.md", "memory/plan-review-scores.md"],
"A/4-B": ["memory/expert-plan-concerns.md"],
"B/pre": ["CONTEXT.md"],
"B/5": ["memory/unit-{name}/test-case-summary.md", "memory/inline-issues.md"],
"B/6": ["memory/unit-{name}/alignment-verdict.md", "memory/unit-{name}/working-example.md"],
"B/7": ["memory/unit-{name}/review-findings.md"]
}
}
What ships with it
55 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.
- install.sh 6.1 KB runs code
- README.md 10 KB
- references/agent-capability-matrix.md 5.6 KB
- references/agent-teams.md 11 KB
- references/context-separation.md 7.6 KB
- references/cross-cutting-protocols.md 22 KB
- references/docs-first-protocol.md 3.0 KB
- references/error-resilience.md 11 KB
- references/expert-output-schema.md 9.6 KB
- references/forbidden-rules.md 3.7 KB
- references/gate-definitions.md 7.0 KB
- references/generation-style-guide.md 11 KB
- references/gotchas.md 3.8 KB
- references/integration-and-review.md 15 KB
- references/phase-a-planning.md 30 KB
- references/phase-a-review.md 18 KB
- references/phase-b-implementation.md 29 KB
- references/phase-b-verification.md 35 KB
- references/review-rubric.md 7.8 KB
- scripts/create-branch.sh 1.2 KB runs code
- workflow/config.yaml 7.5 KB
- workflow/prompts/api-expert.md 1.8 KB
- workflow/prompts/appsec-expert.md 2.9 KB
- workflow/prompts/async-expert.md 3.0 KB
- workflow/prompts/auth-expert.md 1.7 KB
- workflow/prompts/cache-expert.md 2.8 KB
- workflow/prompts/caching-expert.md 1.5 KB
- workflow/prompts/concurrency-expert.md 1.5 KB
- workflow/prompts/convention-expert.md 3.8 KB
- workflow/prompts/db-expert.md 1.7 KB
- workflow/prompts/design-pattern-expert.md 3.4 KB
- workflow/prompts/external-integration-expert.md 3.1 KB
- workflow/prompts/idiom-expert.md 3.7 KB
- workflow/prompts/infra-expert.md 1.5 KB
- workflow/prompts/infrasec-expert.md 3.0 KB
- workflow/prompts/messaging-expert.md 1.5 KB
- workflow/prompts/nosql-expert.md 2.7 KB
- workflow/prompts/observability-expert.md 3.1 KB
- workflow/prompts/performance-expert.md 3.3 KB
- workflow/prompts/rdbms-expert.md 3.0 KB
- workflow/prompts/stability-expert.md 3.0 KB
- workflow/prompts/sync-api-expert.md 2.9 KB
- workflow/prompts/testability-expert.md 3.3 KB
- workflow/scripts/check-sizes.sh 2.9 KB runs code
- workflow/scripts/classify-error.sh 4.2 KB runs code
- workflow/scripts/detect-progress.sh 2.1 KB runs code
- workflow/scripts/extract-diff.sh 1.0 KB runs code
- workflow/scripts/find-dead-code.sh 2.4 KB runs code
- workflow/scripts/manage-sessions.sh 12 KB runs code
- workflow/scripts/retry-budget.sh 934 B runs code
- workflow/scripts/run-tests.sh 2.3 KB runs code
- workflow/scripts/setup-test-env.sh 10 KB runs code
- workflow/scripts/typecheck.sh 806 B runs code
- workflow/scripts/verify-build.sh 1.2 KB runs code
- workflow/templates/report-template.md 1.6 KB
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.
- 8d ago First seen · 470 lines · 169 tokens per session scan A f177c7ed8a4c
simon is a skill published in the GitHub repository SW-in-beta/simon-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 169 tokens to every session and 9,443 once invoked, about $0.0008 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.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…