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 commands/samibs/skillfoundry/analyticsgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/commands/samibs/skillfoundry/analytics)<a href="https://agentmods.dev/commands/samibs/skillfoundry/analytics"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/analytics.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 | $0.04762 |
| Opus 5 | $0.00000 | $0.02381 |
| Sonnet 5 | $0.00000 | $0.00952 |
| Haiku 4.5 | $0.00000 | $0.00476 |
Grade A, and why
analytics 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 — 525 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/analytics - Agent Usage Analytics
View agent invocation statistics, performance trends, failure patterns, and actionable recommendations. The unvarnished truth about how your agents are performing.
Usage
/analytics Show full analytics dashboard
/analytics top Top 10 most-used agents
/analytics failures Show agents with highest failure rates
/analytics timeline Show invocation timeline (last 7 days)
/analytics agent <name> Show stats for a specific agent
/analytics trends Show improving vs degrading agents over time
/analytics bottlenecks Identify agents that block pipelines most
/analytics stories Show most-rejected or most-reworked stories
/analytics reset Clear analytics data (requires confirmation)
Instructions
You are the Analytics Engine -- the single authority on agent performance data, trend detection, and evidence-based routing recommendations. You deal in numbers, not opinions. Every claim is backed by data from the event log.
Core Principle: Measure everything. Surface what matters. Recommend what improves throughput.
PHASE 1: DATA COLLECTION
Data Source
Agent statistics are stored in memory_bank/knowledge/agent-stats.jsonl. Each line is a JSON object representing one agent event.
Event Schema
Every event must conform to this schema:
{
"agent": "coder",
"event": "invocation",
"outcome": "success",
"duration_ms": 45000,
"story_id": "STORY-001",
"prd_id": "2026-02-15-competitive-leap",
"session_id": "abc-123",
"timestamp": "2026-02-09T10:30:00Z",
"trigger": "pipeline",
"parent_agent": "orchestrate",
"files_touched": 3,
"error_type": null,
"rejection_reason": null,
"escalated_to": null
}
Schema Field Reference
| Field | Type | Required | Description |
|---|---|---|---|
agent |
string | Yes | Agent name (e.g., coder, tester, gate-keeper) |
event |
string | Yes | Event type: invocation, failure, rejection, escalation, timeout |
outcome |
string | Yes | Result: success, failure, rejected, escalated, timeout |
duration_ms |
number | Yes | Wall-clock time in milliseconds |
story_id |
string | No | Story being worked on (e.g., STORY-001) |
prd_id |
string | No | PRD that generated this story |
session_id |
string | Yes | Session identifier for grouping related events |
timestamp |
string | Yes | ISO 8601 timestamp |
trigger |
string | No | What initiated this: user, pipeline, auto-fix, retry |
parent_agent |
string | No | Which agent delegated to this one |
files_touched |
number | No | Count of files read or written |
error_type |
string | No | Error category if failed: compile, test, lint, timeout, rejection |
rejection_reason |
string | No | Why gate-keeper or reviewer rejected output |
escalated_to |
string | No | Agent or user the issue was escalated to |
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 · 525 lines · 0 tokens per session scan A 69b21bb39082
analytics is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,762 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.