Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add moberghr/mtk-agent-toolkit/plugin install mtkWrote 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/moberghr/mtk-agent-toolkit/correction-capture)<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/correction-capture"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/correction-capture.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 | $0.00039 | $0.02238 |
| Opus 5 | $0.00019 | $0.01119 |
| Sonnet 5 | $0.00008 | $0.00448 |
| Haiku 4.5 | $0.00004 | $0.00224 |
Grade B, and why
correction-capture scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -i "<keyword>" .claude/lessons/personal.md tasks/lessons.md 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Correction Capture
Overview
When an engineer corrects your approach, that correction contains knowledge that should compound across sessions. Capture it immediately, process it into a reusable lesson, and ensure it loads in future sessions. The goal: the engineer should never need to give the same correction twice.
This skill is specifically for engineer-driven corrections. When you resolve your own repeated failure through trial and error — same signature failing 2+ times, then a materially different fix, with no human redirect — that is self-driven, not a correction: use golden-path-capture instead. (And lesson-mining is the after-the-fact transcript sweep for what neither live skill captured.)
When To Use
- The engineer says "no", "not like that", "stop doing X", "I told you before"
- The engineer redirects your approach mid-task
- The engineer overrides a decision you made
- A review finding reveals a repeated mistake
- A pattern that worked elsewhere fails in this codebase
When NOT To Use
- One-off task-specific feedback that wouldn't apply to future work
- Feedback about conversation style rather than technical approach
- Corrections that are already documented in CLAUDE.md or references
Workflow
-
Recognize the correction. Look for:
- Direct negation: "no", "don't", "stop", "wrong"
- Redirection: "instead do X", "use Y not Z", "the pattern here is..."
- Frustration signal: "I already said", "again", "like I mentioned"
-
Acknowledge without performing. State what you understand changed:
- "Understood — I'll use X instead of Y because [reason]."
- Do not say "You're absolutely right!" or "Great point!" — just state the correction and act on it.
-
Decide where it belongs — personal or team. Two destinations:
.claude/lessons/personal.md(gitignored) — default. Personal preferences, individual workflow tweaks, "I prefer X here".tasks/lessons.md(committed) — team-wide rules. Architectural patterns, repeated team-wide mistakes, conventions every contributor should follow.
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 · 156 lines · 39 tokens per session scan B 0ffbc278223b
correction-capture is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 2,238 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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…