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 hifriendbot/cogmemai-mcp --skill save-bugfixgit clone --depth 1 https://github.com/hifriendbot/cogmemai-mcpWrote 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/hifriendbot/cogmemai-mcp/save-bugfix)<a href="https://agentmods.dev/skills/hifriendbot/cogmemai-mcp/save-bugfix"><img src="https://agentmods.dev/badge/skills/hifriendbot/cogmemai-mcp/save-bugfix/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/hifriendbot/cogmemai-mcp/save-bugfix"><img src="https://agentmods.dev/badge/skills/hifriendbot/cogmemai-mcp/save-bugfix.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 | $0.00097 | $0.01269 |
| Opus 5 | $0.00048 | $0.00634 |
| Sonnet 5 | $0.00019 | $0.00254 |
| Haiku 4.5 | $0.00010 | $0.00127 |
Grade A, and why
save-bugfix 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 9d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Every Bugfix with CogmemAi
Every team wastes hours re-debugging problems that someone already solved. The fix lives in someone's head, buried in Slack, or attached to an old Jira ticket nobody can find. CogmemAi solves this: every bugfix gets saved as a searchable memory, and every new bug starts with a search instead of from-scratch debugging.
This skill is the save half of that loop. Pair it with the search-before-debugging skill for the recall half.
When to Use
Trigger immediately on any of these signals:
- A bug was just fixed and the test/build is now passing
- A flaky test was diagnosed and the root cause identified
- A production incident was resolved
- The user says: "got it", "that fixed it", "it works now", "nailed it", "found it", "the problem was X"
- A non-obvious workaround was applied
- An error message has been understood and resolved
Do not wait for the user to ask. Save proactively the moment the fix is verified.
What to Save
Use save_memory with memory_type: "bug" and capture all four parts. Skipping any of them makes the memory useless for future recall.
1. Symptom (what broke)
The exact error message or observable behavior. Future-you will search for this. Include:
- Verbatim error text or stack trace summary
- Affected component, file, or service
- Conditions under which it appeared (browser, OS, request volume, time of day)
2. Root cause (why it broke)
The actual underlying reason, not the surface trigger. "Login failed because the JWT signing key was rotated last week but the auth service cached the old key in memory." Not "login failed."
3. Fix (what made it work)
The concrete change. Include the file path and the nature of the edit. "Added a 60-second TTL to the JWT key cache in src/auth/keystore.ts." Not "fixed the cache."
4. Why this fix works (mechanism)
One sentence on the mechanism so future readers can judge whether the same fix applies to a similar bug. "Forces re-fetch when keys rotate, at the cost of one extra round trip per minute under load."
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.
- 9d ago First seen · 107 lines · 97 tokens per session scan A b904ce50a17e
save-bugfix is a skill published in the GitHub repository hifriendbot/cogmemai-mcp (7 stars, last pushed 8d ago), licensed MIT. It adds 97 tokens to every session and 1,269 once invoked, about $0.0005 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
mem0-status
Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.
ai4j-app-builder
Use this skill when helping users build applications with AI4J in their own Java or Spring Boot projects, including first chat, streaming, tool/function calls, MCP, RAG, memory, Agent runtime, Coding Agent CLI embedding, FlowGram integration, provider configuration, dependency selection, and troubleshooting. It guides…
honcho-cli
Inspect and debug Honcho workspaces via the honcho CLI. Use when investigating peer representations, memory state, session context, or dialectic quality — any task that requires introspection of a Honcho deployment, including verifying that a recall/record memory loop is actually working.
upload-debug-memory
Use after resolving a bug, test failure, build failure, CI issue, deployment issue, or framework/API pitfall when the verified lesson should be published to Noosphere for future agents.
yesmem-remember
Use after ANY decision, correction, gotcha, or discovery worth preserving. Also on task completion — resolve open tasks via resolvebytext() after commits, "fertig", or confirmed fixes. Trigger on "remember this"/"merk dir das", confirmed approaches, debugging surprises, and relatelearnings() for connecting insights.
agent-debug-memory
Use when debugging code, tests, builds, deployments, CI failures, runtime errors, framework issues, API migrations, or UI state bugs where a coding Agent should consult Noosphere shared memory before fixing and upload the verified lesson afterward.