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/005-supersession-chainsgit 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/005-supersession-chains)<a href="https://agentmods.dev/agents/paulbreuler/limps/005-supersession-chains"><img src="https://agentmods.dev/badge/agents/paulbreuler/limps/005-supersession-chains.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 | $0.00000 | $0.00466 |
| Opus 5 | $0.00000 | $0.00233 |
| Sonnet 5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
005-supersession-chains 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 4d 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 005: Supersession Chains
Objective
Track when documents supersede others, maintaining decision history chains.
Tasks
-
Supersession manager (
src/context/supersession.ts)supersede(oldId, newId): Create supersession link- Update both documents' frontmatter
- Set old document status to 'superseded'
- Build supersession graph
-
Chain traversal
getSupersessionChain(docId): Walk back through historygetCurrentVersion(docId): Follow chain to currentgetSupersededBy(docId): What replaced this?
-
ADR commands
limps adr supersede ADR-0003 ADR-0010— Create linklimps adr history ADR-0010— Show chainlimps adr current ADR-0003— Find current version
-
Automatic updates When ADR-0010 supersedes ADR-0003:
- ADR-0010.supersedes = [ADR-0003]
- ADR-0003.superseded_by = ADR-0010
- ADR-0003.status = 'superseded'
Frontmatter Schema
---
title: "Use sqlite-vec"
type: adr
status: accepted # proposed | accepted | deprecated | superseded
supersedes: [ADR-0003, ADR-0005]
superseded_by: null
---
Acceptance Criteria
-
limps adr supersedeupdates both documents -
limps adr historyshows full chain - Status automatically changes to 'superseded'
- Circular supersession detected and prevented
- Warns if anything references superseded ADR
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.
- 4d ago First seen · 62 lines · 0 tokens per session scan A 01786fdbffb1
005-supersession-chains 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 466 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…
parallel-implementation-orchestrator
Use this agent when the user requests implementation of design documents or specifications that can be broken down into independent, parallelizable work units. This includes scenarios like:\n\n \nContext: User has completed Phase 1 planning for contextgit and wants to begin implementation.\nuser: "Let's start…
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
memory-extractor
Automatically extract and save important information from conversations to ContextFS.