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/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-feedbacknpx skills add synpulse8-opensource/pulse8-ai-cortex-knowledge-vault --skill cortex-feedbackgit clone --depth 1 https://github.com/synpulse8-opensource/pulse8-ai-cortex-knowledge-vaultWrote 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/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-feedback)<a href="https://agentmods.dev/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-feedback"><img src="https://agentmods.dev/badge/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-feedback.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 | $0.00036 | $0.00438 |
| Opus 5 | $0.00018 | $0.00219 |
| Sonnet 5 | $0.00007 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
cortex-feedback 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 4d 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.
What it actually says
Cortex feedback
Storage
- Folder:
{vault}/feedback/ - Filename:
YYYY-MM-DDTHH-MM-SS.md(UTC timestamp) - Module:
cortex/vault/feedback.py
Frontmatter
| Field | Value |
|---|---|
type |
feedback |
status |
OPEN on create |
tags |
list from request |
related_paths |
list of vault-relative .md paths |
created_at |
ISO timestamp |
Validation
related_paths entries must:
- Exist under vault root
- Be files (not directories)
- End with
.md
Raw .txt or missing paths → error. Put filename mentions in content instead.
API
| Method | Path |
|---|---|
| POST | /api/v1/feedbacks |
| GET | /api/v1/feedbacks |
| GET | /api/v1/feedbacks/{filename} |
| DELETE | /api/v1/feedbacks/{filename} |
Response includes status: "OPEN" (not legacy "created").
MCP
vault_feedback— same body as RESTvault_list_feedbacks— metadata only (no full body)
Teams notification
After successful create, notify_new_feedback() in cortex/notify/teams.py posts an Adaptive Card if TEAMS_WEBHOOK_URL is set. Link uses TEAMS_APP_BASE_URL when configured.
Failures to notify are logged; feedback file still created.
Graph
Feedback notes become graph nodes (NodeType.feedback). Edges from related_paths where applicable.
Related skills
- Vault layout:
cortex-vault - API reference:
cortex-api - Deploy Teams env:
cortex-deploy
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.
- 4d ago First seen · 67 lines · 36 tokens per session scan A f1a78ae088a0
cortex-feedback is a skill published in the GitHub repository synpulse8-opensource/pulse8-ai-cortex-knowledge-vault (14 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 438 once invoked, about $0.0002 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
任务链可视化
将 docs/tasks/ 下的任务文件和 .project/ 下的项目文档汇总为单个自包含 HTML，供人类审阅任务链全貌、依赖关系和 AC 追溯覆盖。在方案规划完成后、交付用户审阅前使用。.
grooming
Shape ambiguous work into an agreed, executable plan. Use when the user asks to groom, scope, decompose, or prepare work before implementation.
grooming-evidence
Ground work grooming in existing product evidence. Use while shaping tasks from code, documentation, tracker state, and user feedback.
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.
alembic-migration
Create, review, and apply database schema changes with Alembic. Use whenever a SQLAlchemy model is added or changed, a column/index/constraint needs to change, or a data backfill is required — anything that alters the PostgreSQL schema.
billing-stripe
Work with Stripe billing — subscriptions, plans/prices, the Customer Portal, credits, usage metering, invoices, and webhook events. Use when changing plans, handling a new Stripe webhook, debugging a payment/subscription flow, or touching credit balances and usage.