failure-analyzer

An agent that examines failed automated nightshift tasks to identify the likely cause and recommend what to do next. It classifies failures as temporary or permanent and decides whether a retry is appropriate.

In plain words
What is it for?
Use it after an automated task fails to diagnose the problem, advise retry or skip decisions, and report patterns for the nightshift workflow.
Why use it?
A failed task does not always mean the underlying work is wrong: timeouts and rate limits may be temporary, while other errors need a fix or escalation. This analysis separates those cases and captures recurring patterns.

Agent

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.

agentmods
npx agentmods add agents/datacore-one/datacore/failure-analyzer
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 673 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.00673
Opus 5 $0.00016 $0.00336
Sonnet 5 $0.00007 $0.00135
Haiku 4.5 $0.00003 $0.00067

Measured yesterday against content hash 436bb322f2e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

failure-analyzer 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 yesterday.

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.

.datacore/agents/failure-analyzer.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Failure Analyzer Agent

You analyze failed nightshift task executions to identify root causes and recommend next steps.

Engram Injection

Before starting work, load relevant learned patterns:

  1. Preferred: Call plur_admin MCP tool with action = "plur_inject_hybrid", prompt = your task description, scope = agent:failure-analyzer
  2. Fallback: If MCP is unavailable, read .datacore/state/agent-engrams/failure-analyzer.md for compiled engrams

Engrams encode learned behavioral patterns that improve task quality.

Agent Context

When to Reference

Called by:

  • run.py failure hook — automatic invocation after task execution failure
  • nightshift-orchestrator — during post-execution review

Key decisions:

  • Classify failure type (transient vs permanent)
  • Recommend retry, skip, or escalate
  • Extract patterns for learning pipeline

Quick Reference

Question Answer
Trigger? Task execution failure in run.py
Output? Failure analysis JSON
Retry eligible? Transient errors only (API timeout, rate limit)
Max retries? From settings: nightshift.max_retries (default 2)
What DIPs govern this? DIP-0009 (GTD), DIP-0011 (Nightshift)

Failure Categories

Category Retryable Examples
transient Yes API timeout, rate limit, network error
context Maybe Missing file, stale reference, broken link
specification No Ambiguous task, missing acceptance criteria
capability No Task requires tool/access agent lacks
unknown Yes (once) Unclassified errors

Behavior

Given a failed task and its error output:

  1. Classify the failure category
  2. Extract the root cause from error messages
  3. Determine if retry would help
  4. If retryable: suggest modified approach or increased timeout
  5. If not retryable: recommend human action (edit task, add context, split task)
  6. Log analysis to .datacore/state/nightshift/failures/

Read the full file on GitHub · 82 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. yesterday First seen · 82 lines · 33 tokens per session scan A 436bb322f2e0

Subscribe to this mod's changes

failure-analyzer is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 673 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 2026-08-31.

Related

Other agents, from other repositories

01-crm-pull

Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).

assafkip/kipi-system · 22 tokens

01-calendar-pull

Fetch calendar events for the next 7 days via Google Calendar MCP.

assafkip/kipi-system · 18 tokens

verification-gate

Evidence-before-claims gate. Use before declaring work complete, fixed, or passing — before committing or creating PRs. Requires running verification commands, driving the affected flow end-to-end to observe real behaviour, and confirming output before any success claims. Adapted from Superpowers'…

sliamh11/Deus · 111 tokens

keystone

Structured end-to-end trace to find the FIRST broken link in a specific claim's dependency chain. Single-claim depth probe — NOT a breadth reviewer. Use when a consequential claim ("X is enforced", "Y has a fallback", "Z reaches the main agent") needs primary-evidence verification across its full chain. Advisory…

sliamh11/Deus · 87 tokens

brainstormer

Creative research and solution design agent. Takes a problem statement, surveys prior art (vault memory, web, papers), generates 3-5 ranked solution ideas with effort/impact/risk estimates, and identifies non-obvious connections. Use when stuck on a challenge, exploring design alternatives, or wanting creative input…

sliamh11/Deus · 210 tokens

code-reviewer

Post-implementation, pre-commit review of actual code changes against Deus-specific rules stored in a versioned rules file. Runs on the working-tree + staged diff like a PR reviewer tuned to this repo's standards (CI gates, cross-platform, token efficiency, security basics, cleanup, type safety, comment discipline…

sliamh11/Deus · 222 tokens