AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Context Manager

skill-yiftahb-agsync-context-manager · by yiftahb

>

No reviews yet
0 installs
29 views
0.0% view→install

Install

$ agentstack add skill-yiftahb-agsync-context-manager

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-yiftahb-agsync-context-manager)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Context Manager? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Help the user create or maintain agsync structured context files:

  1. Author .agsync/instructions.md (root or package) and .agsync/patterns/*.md
  2. Migrate from .cursorrules, .cursor/rules/*.mdc, or .coderabbit.yaml
  3. Validate with agsync validate after every write

instructions.md format:

---
extends: root          # omit at root level
apply_patterns:
  - id: pattern-id
    paths: ["subdir/**"]
---

## HLD
Prose description of architecture and intent.

## Guidelines
- id: rule-id
  rule: "the rule, phrased as a constraint"
  override: true       # only if overriding a parent rule with same id

pattern file format (.agsync/patterns/.md):

---
id: pattern-name
---

## HLD
Why this pattern exists.

## Guidelines
- id: rule-id
  rule: "the rule"

Migration rules:

  • .cursorrules flat text → extract imperative lines → propose as guidelines in root instructions.md
  • .mdc with globs: → map globs to paths: on guidelines or apply_patterns
  • .coderabbit.yaml path_instructions → reverse-map each path entry to guidelines with matching paths:
  • Ask before deleting source files
  • Every guideline needs a unique id — use kebab-case, describe the constraint not the action
  • No duplicate rules across packages unless override: true is intentional
  • Paths in guidelines are relative to repo root — backend/** not ./backend/**
  • Run agsync validate before reporting done; fix any errors or warnings
  • Do not add guidelines that restate the obvious — only non-obvious constraints survive

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.