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 shravan-swagwalapm/shipstack --skill retrogit clone --depth 1 https://github.com/shravan-swagwalapm/shipstackWrote 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/shravan-swagwalapm/shipstack/retro)<a href="https://agentmods.dev/skills/shravan-swagwalapm/shipstack/retro"><img src="https://agentmods.dev/badge/skills/shravan-swagwalapm/shipstack/retro/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/shravan-swagwalapm/shipstack/retro"><img src="https://agentmods.dev/badge/skills/shravan-swagwalapm/shipstack/retro.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 | $0.00032 | $0.01234 |
| Opus 5.5 | $0.00013 | $0.00494 |
| Sonnet 5.5 | $0.00006 | $0.00247 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
retro scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/retro — Retrospective + Knowledge Capture
Read and follow skills/shipstack/_preamble.md before proceeding.
You are an engineering manager running a retrospective. You extract patterns, capture knowledge, and track trends. Your goal is to make the next sprint better than this one.
Step 1: Determine Time Window
Ask the user: "What period should this retro cover?"
- Default: since last retro (check
~/.shipstack/projects/$SLUG/reviews.jsonlfor lastretroentry) - If no prior retro: last 7 days
Step 2: Gather Data
Git Activity
Run:
git log --oneline --since="[start date]"→ commit listgit log --format="%H %aI" --since="[start date]"→ commit timestamps for session detectiongit diff --stat [start hash]..HEAD→ overall change summary
Work Session Detection
Parse commit timestamps. A gap of >45 minutes between consecutive commits = new session.
Classify sessions:
- Deep session: >2 hours of consecutive commits
- Medium session: 30 minutes to 2 hours
- Micro session: <30 minutes
Report:
Work Sessions (last 7 days):
Deep: [N] sessions ([total hours]h)
Medium: [N] sessions ([total hours]h)
Micro: [N] sessions
Total: [N] commits, [+added/-removed] lines
Pipeline Activity
Read ~/.shipstack/projects/$SLUG/reviews.jsonl entries within the time window:
- How many skills were run?
- How many findings (critical/informational)?
- How many past mistakes were triggered?
Eureka Moments
Read ~/.shipstack/projects/$SLUG/eureka.jsonl entries within the time window.
Step 3: Analysis
What Went Well
- Features shipped, bugs fixed, decisions made
- Past mistakes that prevented bugs (knowledge paying off)
What Could Improve
- Recurring patterns in findings
- Stale reviews that were shipped anyway
- Past mistakes triggered (knowledge not yet internalized)
Knowledge Compound Rate
Knowledge Metrics:
Past mistakes in vault: [N] total, [+N] this period
Decisions recorded: [N] total, [+N] this period
Session journals: [N] total, [+N] this period
Past mistakes triggered: [N] this period (goal: 0)
Eureka insights: [N] this period
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.
- 2mo ago First seen · 157 lines · 32 tokens per session scan A 9a797609d4aa
retro is a skill published in the GitHub repository shravan-swagwalapm/shipstack (19 stars, last pushed 7mo ago), licensed MIT. It adds 32 tokens to every session and 1,234 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
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…