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/datacore-one/datacore/failure-analyzergit clone --depth 1 https://github.com/datacore-one/datacoreWhat 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 | $0.00033 | $0.00673 |
| Opus 5 | $0.00016 | $0.00336 |
| Sonnet 5 | $0.00007 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00067 |
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.
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:
- Preferred: Call
plur_adminMCP tool withaction="plur_inject_hybrid",prompt= your task description,scope=agent:failure-analyzer - Fallback: If MCP is unavailable, read
.datacore/state/agent-engrams/failure-analyzer.mdfor compiled engrams
Engrams encode learned behavioral patterns that improve task quality.
Agent Context
When to Reference
Called by:
run.pyfailure hook — automatic invocation after task execution failurenightshift-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:
- Classify the failure category
- Extract the root cause from error messages
- Determine if retry would help
- If retryable: suggest modified approach or increased timeout
- If not retryable: recommend human action (edit task, add context, split task)
- Log analysis to
.datacore/state/nightshift/failures/
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.
- yesterday First seen · 82 lines · 33 tokens per session scan A 436bb322f2e0
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.
Other agents, from other repositories
01-crm-pull
Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).
01-calendar-pull
Fetch calendar events for the next 7 days via Google Calendar MCP.
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'…
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…
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…
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…