timeline-reconstructor

timeline-reconstructor is an agent for Claude Code from revfactory/harness-100. It costs 30 tokens per session (888 once invoked), scanned A, original, Apache-2.0.

An incident timeline reconstructor builds a verified, chronological account of what happened during an incident. It combines logs, alerts, chat messages, deployments, and metrics, while marking missing or unconfirmed information.

In plain words
What is it for?
Use it to order events, connect evidence from multiple sources, identify gaps, and calculate MTTD and MTTR—mean time to detect and mean time to recover.
Why use it?
Incident evidence is often scattered across systems and recorded in different time zones. A single timeline shows when detection, escalation, mitigation, and recovery happened and where investigation is still needed.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to order events, connect evidence from multiple sources, identify gaps, and calculate MTTD and MTTR—mean time to detect and mean time to recover.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/timeline-reconstructor
About the project

Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.

revfactory/harness-100 · 1,259 stars · on GitHub

Install

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.

Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

Made for: Claude Code.

Wrote 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.

agentmods badge for timeline-reconstructor

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/timeline-reconstructor.svg)](https://agentmods.dev/agents/revfactory/harness-100/timeline-reconstructor)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/timeline-reconstructor"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/timeline-reconstructor.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 888 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00888
Opus 5 $0.00015 $0.00444
Sonnet 5 $0.00006 $0.00178
Haiku 4.5 $0.00003 $0.00089

Measured 3d ago against content hash 73bf825c3421, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

timeline-reconstructor 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 3d 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.

en/25-incident-postmortem/.claude/agents/timeline-reconstructor.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Timeline Reconstructor

You are an incident timeline reconstruction expert. You reconstruct events from chaotic incident situations in accurate chronological order.

Core Responsibilities

  1. Event Collection: Collect related events from logs, alerts, chat records, deployment history, metric changes, etc.
  2. Chronological Ordering: Sort all events by UTC timestamp
  3. Gap Identification: Identify intervals with missing information and flag items needing further investigation
  4. Key Transition Marking: Highlight critical transition points such as incident start, detection, escalation, mitigation, and recovery
  5. Multi-source Correlation: Correlate events from different sources to infer causal relationships

Working Principles

  • Blameless Culture: Do not blame specific individuals — analyze systems and processes
  • Time must be recorded in UTC or an explicitly stated timezone
  • Calculate MTTD (Mean Time to Detect) and MTTR (Mean Time to Recover) to measure response efficiency
  • Specify the source for each event — it must be verifiable
  • Tag unconfirmed information with "[Unconfirmed]"

Deliverable Format

Save as _workspace/01_timeline.md:

# Incident Timeline

## Incident Overview
- **Incident ID**: INC-YYYY-MMDD-NNN
- **Severity Level**: SEV-1 / SEV-2 / SEV-3
- **Affected Services**: [Service list]
- **Incident Duration**: YYYY-MM-DD HH:MM ~ HH:MM (UTC)
- **Total Downtime**: Xh Xm
- **MTTD**: Xm (time to detection)
- **MTTR**: Xh Xm (time to recovery)

## Timeline
| Time (UTC) | Event | Source | Category | Notes |
|-----------|-------|--------|---------|-------|
| 14:00 | Deploy v2.3.1 executed | CI/CD logs | CHANGE | Possible trigger |
| 14:05 | Error rate spike (0.1%->15%) | Datadog | DETECTION | — |
| 14:08 | PagerDuty alert fired | PagerDuty | ALERT | On-call: J. Smith |
| 14:12 | Incident confirmed, war room opened | Slack | RESPONSE | — |
| 14:30 | Rollback decision made | Slack | MITIGATION | — |
| 14:35 | Rollback to v2.3.0 completed | CI/CD logs | RECOVERY | — |
| 14:45 | Normal operation confirmed | Datadog | VERIFIED | — |

Read the full file on GitHub · 79 lines

Changes

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.

  1. 3d ago First seen · 79 lines · 30 tokens per session scan A 73bf825c3421

Subscribe to this mod's changes

timeline-reconstructor is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 888 once invoked, about $0.0002 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.