Kiro Crew is a persistent development workspace where agents continue multi-step software work across sessions, schedules, and connected interfaces. Developers use it locally or remotely through a desktop app, web dashboard, CLI, Slack, or Discord, with unattended tasks and recurring jobs. The catalogue contains skills and instructions for working with this workspace.
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 agentmods add skills/kirodotdev/kirocrew/learn-from-sagenpx skills add kirodotdev/KiroCrew --skill learn-from-sagegit clone --depth 1 https://github.com/kirodotdev/KiroCrewWrote 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/kirodotdev/kirocrew/learn-from-sage)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/learn-from-sage"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/learn-from-sage.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 | $0.00056 | $0.01902 |
| Opus 5 | $0.00028 | $0.00951 |
| Sonnet 5 | $0.00011 | $0.00380 |
| Haiku 4.5 | $0.00006 | $0.00190 |
Grade A, and why
learn-from-sage 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn from Sage — detection-gap (miss) analysis (V2, file-centric)
Learning is not summarizing what Sage found. It is finding issues that leaked past review and shipped, then working backwards to close the gap so the reviewer catches the next one.
Two files, one rule each:
learned-patterns.md— the canonical, consolidated ruleset. The only file a review loads as heuristics. Human-editable.learned-patterns.candidate.md— append-only staging for new learnings. Reviews do NOT read it. It is merged intolearned-patterns.mdonly when a human triggers consolidation (a one-shot AI merge), after which it's cleared.
The interpreter in every command below
Commands here are written as <python> …. Replace <python> with the absolute
interpreter path the task prompt names — it is the one the app itself runs, and
it is the only interpreter guaranteed to exist on this host. Never substitute a
bare python3: Windows has no such interpreter (the name resolves to a
Microsoft Store app-execution alias that runs nothing), so the command would
stage nothing and the learning would be silently lost. Outside a review
session, use the interpreter running the app.
Self-heal (first)
<python> ~/.kiro/crew/apps/code-review-sage/sage_lib/store.py --ensure
<python> ~/.kiro/crew/apps/code-review-sage/sage_lib/learning.py seed # no-op if already seeded
Admissible sources only (no self-poisoning)
Learn only from human-validated, ground-truth signals:
fix_introduce— a real bug shipped and was fixed (fix → introducing change).human_comment— a reviewer comment that was acted on or recurred.design_outcome— a recorded design-discussion outcome (e.g. a feature reverted).import— a pattern imported from another user.
Sage's own draft findings are NOT a source unless a human published/accepted
them (then they become a human_comment). The reviewer learns from what reality
proved it missed, never from its own opinions. sage_lib/learning.py stage enforces
this — an inadmissible source raises.
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 · 137 lines · 56 tokens per session scan A 4f8f953ca149
learn-from-sage is a skill published in the GitHub repository kirodotdev/KiroCrew (3,661 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 1,902 once invoked, about $0.0003 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
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…
executive-financial-briefing
Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or "how is the business doing". Covers the full P&L picture in one page. Also…
multi-quarter-trend-analysis
Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for "how are we trending", "show me the trend", "track performance over time", "quarter over quarter…
sector-rotation
Identify which market sectors to overweight or underweight based on current macro conditions and sector performance data.
trend-analysis
Analyze price and volume trends for one or more stocks to determine momentum direction and key technical levels.
persistent-notes
Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".