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 xiaolai/echo-sleuth-for-claude --skill experience-synthesisgit clone --depth 1 https://github.com/xiaolai/echo-sleuth-for-claudeWrote 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/xiaolai/echo-sleuth-for-claude/experience-synthesis)<a href="https://agentmods.dev/skills/xiaolai/echo-sleuth-for-claude/experience-synthesis"><img src="https://agentmods.dev/badge/skills/xiaolai/echo-sleuth-for-claude/experience-synthesis/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/xiaolai/echo-sleuth-for-claude/experience-synthesis"><img src="https://agentmods.dev/badge/skills/xiaolai/echo-sleuth-for-claude/experience-synthesis.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 | $0.00062 | $0.01342 |
| Opus 5 | $0.00031 | $0.00671 |
| Sonnet 5 | $0.00012 | $0.00268 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
experience-synthesis 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 10d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experience Synthesis — Learning from Claude's Past
Insight Taxonomy
When analyzing conversations, extract insights in these categories (ordered by durability — values first):
1. Learned Values
Comparative preferences and priority orderings — "X is better than Y".
Signal sources:
- User states "prefer X over Y", "X is better than Y", "X matters more than Y"
- User confirms a comparative statement from Claude ("yes, readability > cleverness")
- Trade-off discussions that resolve into a clear preference
- Statements with "prioritize", "choose X over Y", "the most important thing is"
What to capture: The value choice, both sides of the comparison, and the reasoning. Values are the most durable type of memory — they survive codebase rewrites.
2. Decisions
What was chosen, why, and what alternatives were rejected.
Signal sources:
AskUserQuestiontool calls + the user's response in the next tool_result- Plan mode content (
planContentfield on user records,ExitPlanModetool calls) - Thinking blocks where Claude weighs options
- Assistant text containing "I'll use X instead of Y because..."
What to capture: The decision, the rationale, the alternatives considered, and the context (what problem it solved).
3. Mistakes & Corrections
What went wrong, root cause, and how it was fixed.
Signal sources:
- Tool results with
is_error: true - Bash results containing: error, failed, FAIL, exit code 1, stack trace, traceback, Exception
- User corrections: "no, that's wrong", "revert that", "that broke X"
- Retry patterns: same tool called 2+ times on the same target with different inputs
- Reverted file edits (same file edited, then edited back)
What to capture: What failed, why it failed, what fixed it, how to avoid it next time.
4. Effective Patterns
Approaches that worked well and could be reused.
Signal sources:
- Successful test runs (Bash results with: passed, PASS, success, 0 errors)
- Successful builds (built in, compiled, no errors)
- PR creation (
pr-linkrecords) - Git commits (successful completion of work)
- User satisfaction signals: "perfect", "great", "exactly what I needed"
What ships with it
1 file 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.
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.
- 10d ago First seen · 149 lines · 62 tokens per session scan A e163141fec35
experience-synthesis is a skill published in the GitHub repository xiaolai/echo-sleuth-for-claude (9 stars, last pushed 16d ago), licensed ISC. It adds 62 tokens to every session and 1,342 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.