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 1999AZZAR/project-guardian-mcp-server --skill guardian-sessiongit clone --depth 1 https://github.com/1999AZZAR/project-guardian-mcp-serverWrote 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/1999azzar/project-guardian-mcp-server/guardian-session)<a href="https://agentmods.dev/skills/1999azzar/project-guardian-mcp-server/guardian-session"><img src="https://agentmods.dev/badge/skills/1999azzar/project-guardian-mcp-server/guardian-session/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/1999azzar/project-guardian-mcp-server/guardian-session"><img src="https://agentmods.dev/badge/skills/1999azzar/project-guardian-mcp-server/guardian-session.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 | $0.00046 | $0.00894 |
| Opus 5 | $0.00023 | $0.00447 |
| Sonnet 5 | $0.00009 | $0.00179 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
guardian-session 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 11d 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.
Guardian Session — Context Loader
Purpose
Each session starts fresh. This skill restores context from memory.db so you know what's been done, what's in progress, and what needs attention next.
When to Load
- At the start of every coding session
- When switching between projects
- When resuming work after a break
- When the user says "what was I working on?"
Core Workflow
1. Load Project State
Search for the current project or topic first:
search_nodes query="<project-or-topic>"
Use read_graph only when the graph is known to be small or a full view is explicitly needed. Scan for:
- Project entities (root nodes)
- Active tasks (not marked
[COMPLETE]) - Open bugs (not marked
[FIX]) - Recent observations (check
updated_at)
2. Contextualize to Current Directory
If working in a subdirectory, search for relevant files:
search_nodes query="file:<current-dir>"
If working on specific files, search for those:
search_nodes query="file:<filename>"
3. Surface Active Work
Find incomplete tasks:
query_data table="entities" conditions={"entity_type": "task"} limit=20
Find open bugs:
query_data table="entities" conditions={"entity_type": "bug"} limit=10
Find recent changes:
query_data table="entities" conditions={} orderBy="updated_at" orderDirection="DESC" limit=10
4. Build Session Summary
Create a mental model of the project state:
PROJECT: <name>
├── ACTIVE TASKS: <count>
│ ├── task:<id>:<title> — <status from observations>
│ └── ...
├── OPEN BUGS: <count>
│ ├── bug:<id>:<slug> — <severity>
│ └── ...
├── RECENT CHANGES: <count>
│ ├── <file or entity> — <what changed>
│ └── ...
└── NEXT UP: <suggested next action based on dependencies>
5. Report to User
Provide a concise briefing:
- What was last worked on (most recent observation)
- What's currently in progress (active tasks)
- What's blocking progress (open bugs, dependency chains)
- Suggested next action
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 150 lines · 46 tokens per session scan A 6c40827f2671
guardian-session is a skill published in the GitHub repository 1999AZZAR/project-guardian-mcp-server (3 stars, last pushed 11d ago), licensed MIT. It adds 46 tokens to every session and 894 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 2026-08-31.
Other skills, from other repositories
memora
Use when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.
sibyl
Persistent memory and task coordination for this project. Invoke for any prompt about past work, project state, in-progress tasks, prior decisions, gotchas, or capturing a non-obvious learning. Also covers semantic search across project knowledge and external docs.
project-context-loader
Load relevant memory, decisions and contacts for the current project at the start of a session.
issue-management
Create, update, list and search GitHub issues and PRs, list a repository's labels, run milestones, and check for duplicates.
hmem-activate
Switch active project mid-session via loadproject, then fix any misrouted O-entry exchanges. Use when the user says 'aktiviere/lade Projekt X', 'switch to project Y', or whenever you'd otherwise call loadproject mid-session.
project-boards
Put issues and pull requests on a GitHub project board, set their fields, read what is on a board, and take items off it.