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/paulbreuler/limps/004-staleness-detectiongit clone --depth 1 https://github.com/paulbreuler/limpsWrote 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/paulbreuler/limps/004-staleness-detection)<a href="https://agentmods.dev/agents/paulbreuler/limps/004-staleness-detection"><img src="https://agentmods.dev/badge/agents/paulbreuler/limps/004-staleness-detection.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 | $0.00000 | $0.00419 |
| Opus 5 | $0.00000 | $0.00210 |
| Sonnet 5 | $0.00000 | $0.00084 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
004-staleness-detection 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 5d 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.
What it actually says
Agent 004: Staleness Detection
Objective
Detect stale context files and surface freshness warnings.
Tasks
-
Staleness calculator (
src/context/staleness.ts)calculateStaleness(doc): Return score 0-1- Compare
updatedto expected refresh interval - Default thresholds: warning=14d, critical=30d, archive=90d
- Per-document
refresh_intervalfrontmatter override
-
Staleness scoring
interface StalenessScore { score: number; // 0-1 (higher = more stale) status: 'fresh' | 'warning' | 'critical'; daysOld: number; recommendedAction: 'none' | 'review' | 'archive'; } -
Health CLI (
src/cli/commands/context/health.ts)limps context health— Check all context fileslimps context health --stale— Only show stalelimps context health <plan>— Scope to plan- Output includes staleness status for each file
-
Freshness in context resolution
- Include staleness info when resolving context
- Warn if inherited context is stale
--no-warningsto suppress
Acceptance Criteria
-
limps context healthshows staleness for all files - Warning at 14 days, critical at 30 days (configurable)
- Context resolution warns about stale inheritance
- Per-file
refresh_intervaloverrides defaults - Archive recommendation at 90 days
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.
- 5d ago First seen · 54 lines · 0 tokens per session scan A 7601d16ffec4
004-staleness-detection is an agent published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 419 tokens. 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
timps_context_briefing
Get a 3-sentence resumption briefing from the Context Keeper: what you were working on, current state (uncommitted changes, broken tests), and recommended next step. Use when the user says 'what was I doing' or 'catch me up'. Use the timpscontextbriefing MCP tool to perform this task. Do not answer directly — delegate…
memory-extractor
Automatically extract and save important information from conversations to ContextFS.
design-reviewer
Design-review sub-agent. Reviews design docs across the four dimensions of architecture, interface, performance, and security, covering MemOS's multi-memory / multi-storage backend constraints.
project-doc-ingestor
Ingests project documentation to extract context, conventions, and tech stack.
aggressive
This project keeps a local, user-owned knowledge graph of its reasoning: Decisions and their reasons, Principles, Cautions that bit us, Problems and Resolutions, Insights, open Intents, Anchors that cluster them. Not code structure — the code holds that. What good capture buys: the next session starts already knowing…
architect
System architect for designing the Hebb Mind agent memory framework.