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/cdeust/cortex/cortex-debug-memorynpx skills add cdeust/Cortex --skill cortex-debug-memorygit clone --depth 1 https://github.com/cdeust/CortexWhat 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 | $0.00087 | $0.00843 |
| Opus 5 | $0.00044 | $0.00421 |
| Sonnet 5 | $0.00017 | $0.00169 |
| Haiku 4.5 | $0.00009 | $0.00084 |
Grade A, and why
cortex-debug-memory 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 yesterday.
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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Memory — Fix, Rate, Protect, and Restore
Keywords
debug, fix, bad memory, wrong, delete, forget, protect, rate, quality, restore, checkpoint, undo, stale, incorrect, mark useful, mark not useful, anchor, unprotect
Overview
Tools for maintaining memory quality — rate memories as useful or not, protect critical ones from decay, forget incorrect ones, validate against the filesystem, and restore from checkpoints when things go wrong.
Use this skill when: Recall returns wrong results, memories are stale, you need to undo changes, or you want to improve retrieval quality through feedback.
Workflow
Fix Bad Memories
Soft delete (sets heat to 0, memory still exists but won't surface):
cortex:forget({
"memory_id": <id>,
"hard": false
})
Hard delete (permanent removal):
cortex:forget({
"memory_id": <id>,
"hard": true
})
Protected memories require "force": true to delete.
Rate Memory Quality
Provide feedback to train the metamemory confidence model:
cortex:rate_memory({
"memory_id": <id>,
"useful": true
})
Or mark as not useful:
cortex:rate_memory({
"memory_id": <id>,
"useful": false,
"reason": "outdated — we no longer use this approach"
})
Ratings adjust the memory's confidence score, which affects future retrieval ranking. Over time, this trains the system to surface better results.
Protect Critical Memories
Anchor a memory (heat=1.0 permanently, injected at session start):
cortex:anchor({
"memory_id": <id>,
"reason": "Core architecture decision — never decay"
})
Validate Against Reality
Check if memories reference things that still exist:
cortex:validate_memory({
"directory": "<project root>"
})
Returns a list of stale memories (referencing deleted files, moved modules, etc.) that should be forgotten or updated.
Checkpoint and Restore
Save a checkpoint before risky operations:
cortex:checkpoint({
"action": "save",
"label": "before-cleanup"
})
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.
- yesterday First seen · 130 lines · 87 tokens per session scan A 0405a094c969
cortex-debug-memory is a skill published in the GitHub repository cdeust/Cortex (71 stars, last pushed 3d ago), licensed MIT. It adds 87 tokens to every session and 843 once invoked, about $0.0004 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
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
genesis-development
This skill should be used when developing, debugging, refactoring, or building Genesis itself — tasks like "fix this in Genesis", "add a new MCP tool", "wire up the runtime", "Genesis won't start", "create a worktree", "debug the bridge", or "add a capability". Applies to any task modifying files under src/, .claude/…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.