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 tomzx/agents --skill create-learningsgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/create-learnings)<a href="https://agentmods.dev/skills/tomzx/agents/create-learnings"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-learnings/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/tomzx/agents/create-learnings"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-learnings.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 | $0.00022 | $0.00711 |
| Opus 5.5 | $0.00009 | $0.00284 |
| Sonnet 5.5 | $0.00004 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
create-learnings scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Learnings
Runs a retrospective to capture actionable learnings after completing a feature, sprint, or project. Produces a structured document covering what went well, what didn't, process improvements, technical insights, and next actions.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - If no argument is provided, locate the feature directory under
.sdlc/features/whose frontmatterissuefield references$ISSUE_NUMBER. - A completed feature, sprint, or project to reflect on
- Context about what was built, how long it took, and any notable events
- If any files exist under
.sdlc/knowledge/assumptions/or.sdlc/knowledge/decisions/for this feature, review them for context.
Steps
- Gather context: what was delivered, timeline, team involved, and any notable events.
- Reflect on what went well (practices worth repeating and amplifying).
- Reflect on what didn't go well, identifying root causes not just symptoms.
- Identify concrete process improvements with owners and dates.
- Capture technical insights: decisions that paid off and decisions to revisit.
- Distill actionable next steps.
- Write the output to
.sdlc/knowledge/learnings/N-<slug>.mdwhere N is the next available sequence number in that directory.
Output Format
Use the template at skills/sdlc/templates/knowledge/learning.md (copied to .sdlc/templates/knowledge/learning.md by /initialize-sdlc-directory; use the project's customized copy if present).
Write the result to the artifact path named in the steps above.
Outcome
If $OUTCOME_YAML is set, emit verdict: approved there per skills/sdlc/references/shared.md once the learnings artifact is written.
In the same emission, list the artifact under artifacts: (.sdlc/knowledge/learnings/N-<slug>.md).
Example Usage
Scenario 1: Feature retrospective A payment feature took 3 weeks instead of 2. Learnings: the third-party API was underdocumented (add a spike phase to future plans involving new integrations), automated integration tests caught 4 regressions early (keep and expand), the spec was changed mid-implementation (add a spec-freeze milestone to the plan template).
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.
- 22d ago Changed · -1 lines ea964cad6247
- 23d ago Changed · -4 lines 95685be96173
- 24d ago Changed c3c08519acbb
- 2mo ago First seen · 67 lines · 22 tokens per session scan A 5194cbd2e476
create-learnings is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 711 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…