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 irisxc4/memoryguard --skill memoryguard-local-opsgit clone --depth 1 https://github.com/irisxc4/memoryguardWrote 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/irisxc4/memoryguard/memoryguard-local-ops)<a href="https://agentmods.dev/skills/irisxc4/memoryguard/memoryguard-local-ops"><img src="https://agentmods.dev/badge/skills/irisxc4/memoryguard/memoryguard-local-ops/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/irisxc4/memoryguard/memoryguard-local-ops"><img src="https://agentmods.dev/badge/skills/irisxc4/memoryguard/memoryguard-local-ops.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 | $0.00051 | $0.02025 |
| Opus 5.5 | $0.00020 | $0.00810 |
| Sonnet 5.5 | $0.00010 | $0.00405 |
| Haiku 4.5 | $0.00005 | $0.00202 |
Grade A, and why
memoryguard-local-ops 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 1mo 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MemoryGuard local operations
Use this skill for the repository's agent-memguard package (the current
checkout declares version 0.7.11). Scope is local Windows installation,
configuration, repair, diagnostics, and governed memory operations.
This is a skills-only plugin. It does not bundle agent-memguard, add a
remote MCP server, or silently edit a user's host configuration. Run commands
only when the user asked for the corresponding operation; use read-only checks
first when diagnosing.
Windows install
-
Check the interpreter and package manager:
py -3 --version py -3 -m pip --version py -3 -c "import sys; print(sys.executable)"agent-memguardrequires Python 3.10 or newer. If thepylauncher is not available, usepythonconsistently and verify that it resolves to the interpreter that will run the MCP process. -
Install or upgrade the PyPI package:
py -3 -m pip install --upgrade agent-memguardThe optional desktop console is a separate extra:
py -3 -m pip install --upgrade "agent-memguard[gui]"For a source checkout, use a non-editable install (
py -3 -m pip install .). Do not point a live Codex MCP process atsrcor usepip install -eas its runtime. The provider installer can select or build a content-keyed, non-editable runtime snapshot when it detects a local/editable install. -
Verify the exact interpreter and package:
memoryguard --version py -3 -c "import importlib.metadata as m; print(m.version('agent-memguard'))" py -3 -m memoryguard.mcp_server --help memoryguard doctorIf
memoryguardresolves to another Python installation, use that interpreter's console-script path or repairPATH; do not assume that a successfulpipcommand configured Codex.
Codex configuration
Preferred provider path
If the MemoryGuard MCP tools are already available, call:
memoryguard_provider_install(provider="codex")
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.
- 1mo ago Changed cf11a42241df
- 1mo ago First seen · 226 lines · 51 tokens per session scan A 0f058465caa4
memoryguard-local-ops is a skill published in the GitHub repository irisxc4/memoryguard (3 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 2,025 once invoked, about $0.0002 per session on Opus 5.5. 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
deja-search
Search deja before re-deriving past work: when the user refers to earlier sessions or decisions, before debugging an error, and before implementing something that may already exist. It searches this machine's own history across every AI coding tool used on it, going back further than deja itself was installed.
deja-history
Search the user's past AI coding sessions. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you…
brain-page
Operating manual for reading and writing a project's brain — every read and write goes through the bundled zero-dependency brain CLI; never hand-edit brain files. Read it before creating or modifying any page or root page.
brain-setup
Bootstrap the Open Project Brain Standard into the current project — prefer brain init (ensure BRAIN.md, scaffold empty brain brainRoot-aware, default-wire CLAUDE.md + AGENTS.md). Optionally install a pre-commit hook and a Claude Code or Codex SessionStart hook.
brain-bootstrap
Seed a freshly-scaffolded brain with real project knowledge — on an existing (brownfield) project read the code, docs, and git log to draft the six root pages and capture key historical decisions; on a near-empty (greenfield) project interview the user. Every write goes through the brain CLI. Run it after brain-setup.
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.