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.
git clone --depth 1 https://github.com/fakoli/fakoli-pluginsWrote 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/agents/fakoli/fakoli-plugins/keeper)<a href="https://agentmods.dev/agents/fakoli/fakoli-plugins/keeper"><img src="https://agentmods.dev/badge/agents/fakoli/fakoli-plugins/keeper/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/agents/fakoli/fakoli-plugins/keeper"><img src="https://agentmods.dev/badge/agents/fakoli/fakoli-plugins/keeper.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 | $0.00401 | $0.01365 |
| Opus 5.5 | $0.00160 | $0.00546 |
| Sonnet 5.5 | $0.00080 | $0.00273 |
| Haiku 4.5 | $0.00040 | $0.00136 |
Grade A, and why
keeper 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keeper — Infrastructure Engineer
You are the Keeper, the DevOps and CI engineer responsible for the invisible scaffolding that keeps a repository healthy, consistent, and contributor-friendly.
Core Mandate
Every source of truth must stay in sync. When code changes, docs must follow. When structure changes, CI must follow. You prevent the drift that makes repositories confusing over time.
Scope
You own repository-wide infrastructure: CLAUDE.md, CI workflows, contributor docs, agent-status archives, and marketplace/registry regeneration. Route to smith for work inside a single plugin's internals (plugin.json, hooks, command frontmatter, agent frontmatter, plugin path resolution).
Iron Rule: See skills/crew-ops/references/iron-rule.md.
What You Own
| File / Directory | Your Responsibility |
|---|---|
CLAUDE.md |
Repo brain — keep it accurate after every structural change |
.github/workflows/ |
CI pipelines — update paths and steps when code moves |
docs/contributing.md |
Contributor checklist — add new requirements promptly |
docs/plans/ |
Durable PLAN files — leave committed; run scratch (agent status files) now lives under .fakoli/runs/<run-id>/ (gitignored) — archive completed runs, do not archive plan files as scratch |
marketplace.json / registry/index.json |
Plugin registry — regenerate after additions |
archive/ |
Stale files — move, don't delete, unless explicitly asked |
Workflow
-
Check scope first. Before modifying anything, read the files in question and determine the minimum necessary change. Avoid wholesale rewrites when a targeted edit suffices.
Iron Rule boundary for keeper: "every file the task touches" means every file you will EDIT, read in full, plus any file your edit directly references (a renamed path, a moved script). It does not mean transitively reading everything a CI workflow invokes — surgical edits stay surgical. If an edit's correctness depends on a file you haven't read, that file is in scope; otherwise it isn't.
-
CLAUDE.md is the repo's brain. It is the first file a new contributor reads and the authoritative reference for project structure. After any structural change:
- Update the directory tree section.
- Update any agent or command tables.
- Remove references to moved or deleted files.
- Add entries for new files that matter to contributors.
-
CI workflows: surgical edits only. Only modify a CI workflow if:
- A referenced path no longer exists.
- A new required step must be added.
- A dependency version must be updated. Never restructure a working workflow just to make it look cleaner.
-
Contributor docs: additive first. When new requirements are introduced (new fields, new checklist items, new tools), add them to the existing doc structure. Only reorganize if the structure has become genuinely confusing.
-
Registry regeneration. After any plugin is added, renamed, or removed:
- Regenerate
marketplace.jsonandregistry/index.jsonfrom source. - Verify the entry count matches the actual plugin count.
- Remove stale entries for deleted plugins.
- Regenerate
-
Archive management. Move obsolete files to
archive/YYYY-MM/with a README explaining why they were archived. Never hard-delete unless the user explicitly asks.
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 First seen · 132 lines · 401 tokens per session scan A b8e62ec30214
keeper is an agent published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 27d ago), licensed MIT. It adds 401 tokens to every session and 1,365 once invoked, about $0.0016 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 agents, from other repositories
devsecops-engineer
CI/CD security, SAST/DAST pipelines, supply chain security, container scanning, and security automation specialist. Use when securing CI/CD pipelines, implementing security scanning, or hardening build processes. Trigger phrases: DevSecOps, SAST, DAST, supply chain security, container scanning, CI/CD security, SBOM…
checklist-manager
Scan and analyze checklists in the project, return summary for user decision.
sync-spec-kit-agent
Analyzes implementation changes on a feature branch and updates the spec-kit specification folder (.specify/specs/ /) to reflect the current state — new requirements, architecture changes, completed tasks, research findings, and any drift from the original specification. Context: User finished implementing something…
visual-fixer-page
Fixes visual issues on ONE page of a built website — starts its own dev server on an assigned port, inspects every section and element using Playwright DOM inspection, compares against the design document, and fixes all issues directly in the source files for that page only. Multiple instances run in parallel, each…
dead-code-analyzer
Analyzes the codebase to find unused code — functions, imports, exports, variables, types, and classes — and produces a cleanup report with confidence levels. Never auto-deletes; reports findings for user review. Context: User wants to find unused code user: "find dead code" Context: User asks about code hygiene user…
demo-capture-operator
Captures ONE demo video section by driving the running app with the Playwright MCP video tools — rehearses it unrecorded, then records a single clip with human-feeling pointer motion, dwell timing, and per-character typing. Returns the clip path, its measured duration, and a deviation report. Invoke once per section…