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/hjertefolger/cortex/cortex-managenpx skills add hjertefolger/cortex --skill cortex-managegit clone --depth 1 https://github.com/hjertefolger/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 | $0.00018 | $0.00955 |
| Opus 5 | $0.00009 | $0.00477 |
| Sonnet 5 | $0.00004 | $0.00191 |
| Haiku 4.5 | $0.00002 | $0.00096 |
Grade A, and why
cortex-manage 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 2d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Management
Help the user manage their Cortex memories.
Capabilities
Search and View Memories
Use cortex_recall to find specific memories:
- Search by content
- Filter by project
- View memory details
Update Memory
Use cortex_update to edit a memory:
- Update content (will re-generate embedding)
- Move to different project
- Both at once
cortex_update(memoryId: 123, content: "corrected content")
cortex_update(memoryId: 123, projectId: "new-project")
Rename Project
Use cortex_rename_project to move all memories from one project to another:
- Useful when project directory is renamed
- Bulk operation - moves all memories at once
cortex_rename_project(oldProjectId: "old-name", newProjectId: "new-name")
Delete Specific Memory
Use cortex_delete to remove a memory fragment:
- First call WITHOUT
confirm: trueto preview what will be deleted - Show the user the preview (content, project, timestamp)
- Ask for explicit confirmation
- If confirmed, call with
confirm: trueto delete
Forget Project Memories
Use cortex_forget_project to delete all memories for a project:
- First call WITHOUT
confirm: trueto get count - Show the user how many memories will be deleted
- Ask for explicit confirmation
- If confirmed, call with
confirm: trueto proceed
Important Safety Rules
ALWAYS follow these rules for destructive actions:
- Preview First: Always call the delete/forget tool without confirm first
- Show Impact: Display exactly what will be affected
- Explicit Confirmation: Ask user "Are you sure you want to delete X?"
- Never Assume: Don't delete without explicit user approval
- Be Clear: State what will be permanently lost
Example Flows
Updating a Memory
User: "Fix the typo in memory 42"
-
First recall to see the memory:
cortex_recall(query: "...") -
Update with corrected content:
cortex_update(memoryId: 42, content: "corrected content here")
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.
- 2d ago First seen · 150 lines · 18 tokens per session scan A 130a01ca92a0
cortex-manage is a skill published in the GitHub repository hjertefolger/cortex (174 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 955 once invoked, about $0.0001 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
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…