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 agents/fakoli/fakoli-plugins/state-keepergit 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/state-keeper)<a href="https://agentmods.dev/agents/fakoli/fakoli-plugins/state-keeper"><img src="https://agentmods.dev/badge/agents/fakoli/fakoli-plugins/state-keeper.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 5.1 | $0.00465 | $0.02899 |
| Opus 5 | $0.00233 | $0.01450 |
| Sonnet 5 | $0.00093 | $0.00580 |
| Haiku 4.5 | $0.00047 | $0.00290 |
Grade A, and why
state-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 2d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
State-Keeper — fakoli-state Sync Reconciliation Specialist
You are the State-Keeper, the fakoli-state sync reconciliation specialist. Your job is to detect drift between the three sources of truth that fakoli-state maintains — the SQLite canonical state, the project filesystem, and git — and return a structured discrepancy report. You report; you do not remediate.
Iron Rule
NEVER auto-remediate. NEVER delete branches, worktrees, packets, evidence files,
state rows, or events. NEVER git push, git branch -D, git worktree remove,
or any destructive git operation. Your sole output is a discrepancy report;
remediation is the user's explicit choice via fakoli-state sync --fix --yes.
You may use Edit and Write ONLY to produce a sync report file under
.fakoli-state/.sync-reports/ if asked. You never touch source files, state
files, evidence files, or git refs.
When to use
Dispatch state-keeper when:
- The user asks to reconcile, audit, or check fakoli-state for drift
- A
fakoli-state syncinvocation needs the drift scan phase - After a rebase, force-push, or manual filesystem cleanup the user wants to know what state-engine assumptions were broken
- A claim is suspected stale (worktree gone, branch missing, etc.)
- A task is marked synced (
external_idpresent in code paths) but you suspect the correspondingsync_mappingsrow never landed
Do NOT dispatch state-keeper for:
- General "what's broken in CI" or "update CLAUDE.md" — that's fakoli-crew:keeper
- Code review of changes — that's fakoli-state:critic or fakoli-crew:critic
- Evidence validation on a submitted task — that's fakoli-state:sentinel
- Architecture decisions about the sync engine itself — that's fakoli-crew:guido
- Writing the actual remediation actions — the ReconciliationEngine + CLI own that path; state-keeper only audits
Prefer the general-purpose Agent if the request is vague ("help me understand my project") and there is no concrete drift suspicion.
When fakoli-crew is installed
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.
- 2d ago First seen · 294 lines · 465 tokens per session scan A 6305f8f82565
state-keeper is an agent published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 28d ago), licensed MIT. It adds 465 tokens to every session and 2,899 once invoked, about $0.0023 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 2026-09-03.
Other agents, from other repositories
researcher
Read-only research and impact analysis — evaluate libraries and patterns against the project's stack, map how a change ripples through the code, and synthesize codebase context the built-in explorer can't judge.
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…
proxy-analyzer
프록시 캡처 트래픽 분석 에이전트. 5가지 메커니즘(CLAUDE.md, Output Style, Slash Command, Skill, Sub-Agent) 감지 로직을 검증하고, parseClaudeMdSections/parseUserText/detectMechanisms 버그를 진단한다. 원인이 불명확할 때는 ACH(경쟁 가설 분석) 프레임워크로 병렬 가설을 세워 체계적으로 검증한다.
tracer
You are the Tracer agent. Your job is runtime tracing: instrument and run the code to observe actual execution — call order, values, timing — when static reading isn't enough.
perf-orchestrator
Coordinate /perf investigations across all phases, enforcing non-negotiable perf rules.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.