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 Adelie-Squad/solosquad --skill retrospectivegit clone --depth 1 https://github.com/Adelie-Squad/solosquadWrote 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/adelie-squad/solosquad/retrospective)<a href="https://agentmods.dev/skills/adelie-squad/solosquad/retrospective"><img src="https://agentmods.dev/badge/skills/adelie-squad/solosquad/retrospective.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.00755 |
| Opus 5 | $0.00023 | $0.00378 |
| Sonnet 5 | $0.00009 | $0.00151 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
retrospective 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.
What it actually says
Retrospective Skill
Chief 가 cycle (workflow / goal / weekly) 종료 시 호출. 객관적 metric + 패턴 식별 + 액션 항목 도출.
입력
- 종료된 workflow id / goal id / period (e.g. last 7d)
<org>/memory/chief-stage-events.jsonl— stage 전환 trace<org>/memory/ledger/<task-id>.jsonl— task event ledger<org>/memory/agent-costs.jsonl— agent 별 USD 소비<org>/memory/leading-indicators.jsonl— 누적 지표
Per-Contributor Breakdown (gstack 차용)
per_contributor:
founder:
inputs: <N> # 사용자 메시지 수
decisions: <N> # batch 답변 / explicit approval 수
chief:
stages_executed: <N>
open_questions_batched: <N>
pm:
spawns: <N>
design_docs_produced: <N>
open_questions_resolved: <N>
avg_confidence: 0-100
engineer:
prs_shipped: <N>
test_coverage_delta: <%>
designer:
specs_produced: <N>
prototypes: <N>
marketer:
campaigns: <N>
content_assets: <N>
Shipping Streak
shipping_streak:
current_days: <N> # 연속 release / merge 일수
best: <N>
threshold: ">=7 stable, <7 yellow"
Confidence Score 갱신
period 내 PM 가설 confidence 평균:
avg_confidence:
start_of_period: 0-100
end_of_period: 0-100
delta: <+/->
reasoning: "string"
출력
period: "..." # workflow id 또는 ISO 날짜 범위
metrics: { per_contributor, shipping_streak, avg_confidence }
what_worked: ["..."]
what_didn_work: ["..."]
patterns_observed: ["..."]
action_items:
- { owner: chief|pm|engineer|..., action: "...", target_date: "YYYY-MM-DD" }
followup_skills:
- skill-refinement # 호출 권고 시
- workflow-refinement # 호출 권고 시
Anti-Sycophancy
- ❌ "잘 한 점이 많네요"
- ✅ "5/7 일 ship 성공. miss 2건 모두 weekend 의존 task. Y 면 weekend 의존 task 분리 권고."
Reference
- gstack
/retroper-contributor breakdown - RO-PNA Confidence Score
- v1.1 PRD §5.2 (Chief RETROSPECT stage)
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 · 103 lines · 46 tokens per session scan A c36aef5b4795
retrospective is a skill published in the GitHub repository Adelie-Squad/solosquad (19 stars, last pushed 18d ago), licensed MIT. It adds 46 tokens to every session and 755 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
gr-product-dev-ops
🇺🇸 Your dev team ships features nobody asked for while user-reported bugs pile up for months. Operations blames engineering for ignoring users; engineering blames operations for not understanding technical constraints. This gives you the complete Product × Engineering × Operations alignment SOP — from unified…
scrumboy-board-operator
Operate Scrumboy projects and boards through MCP or Agoragentic APIs. Use when an agent needs to inspect board state, plan sprint work, create todos, move cards, manage tags, or summarize project health.
pm-skills
Use when coordinating project-delivery work across the 8 project-management sub-skills — sprint/velocity analytics, portfolio health, Jira/JQL, Confluence, Atlassian admin, templates, meeting analysis, team comms. Triggers on 'our sprints feel off', 'project health report', 'audit our Jira permissions', 'when will it…
run-team-retrospective
Use when a team needs to reflect on a completed period, project, or significant event — to extract what worked, what didn't, and what specific changes to make before the next cycle, rather than repeating the same patterns.
teamretro-post-recommendations
Use when the user wants the AI's retro recommendations prepared and posted into TeamRetro — "post the AI's recommendations to TeamRetro", "prep our TeamRetro retro with the AI's findings", "park the top fixes for next retro", "add the AI's feedback to Friday's retro". Do NOT use for general TeamRetro administration…
deal-desk
Deal desk: reviews, approves, and structures non-standard sales deals. Use when standing up a deal desk, building approval-threshold matrices, designing deal-review packets, routing deals, or auditing deals for compliance.