Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/studioKjm/ai-harness-templatenpx agentmods add commands/studiokjm/ai-harness-template/observe-sloWrote 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/studiokjm/ai-harness-template/observe-slo)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/observe-slo"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/observe-slo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/observe-slo"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/observe-slo.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00026 | $0.01698 |
| Opus 5 | $0.00013 | $0.00849 |
| Sonnet 5 | $0.00005 | $0.00340 |
| Haiku 4.5 | $0.00003 | $0.00170 |
Grade A, and why
observe-slo 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/observe-slo — Service Level Objectives
SLI = what we measure. SLO = what we promise. Error Budget = what we can spend.
When to use
- Service has user-facing reliability target
- Deciding "is it ready to ship?" requires measurable bar
- Track reliability across releases (without SLOs every change feels arbitrary)
- Tying ops investment to user impact
Usage
/observe-slo new <slug> \
--service NAME \
--sli-good "QUERY" \
--sli-valid "QUERY" \
--target PCT \
--window "30d"
/observe-slo list [--status proposed|active|retired]
/observe-slo show <slo-id>
/observe-slo activate <slo-id> # proposed → active
/observe-slo retire <slo-id> # active → retired
/observe-slo record-violation <slo-id> --duration MIN --burn-rate RATE [--incident-id ID]
State machine
[proposed] → [active] → [retired]
| State | Meaning |
|---|---|
| proposed | Defined but not yet enforcing alerts |
| active | Measuring + alerting + reporting |
| retired | Replaced by newer SLO or feature deprecated |
Instructions
Step 1 — Define SLI before writing SLO
The SLI (Service Level Indicator) is a ratio: good_events / valid_events.
Examples by SLO type:
Availability SLO:
good_events: rate(refund_request_total{status_code!~"5.."}[5m])
valid_events: rate(refund_request_total[5m])
target: 99.5%
Latency SLO:
good_events: rate(refund_request_total{le="500"}[5m]) # under 500ms
valid_events: rate(refund_request_total[5m])
target: 95%
Quality SLO (if data integrity matters):
good_events: rate(refund_validation_total{outcome="valid"}[5m])
valid_events: rate(refund_validation_total[5m])
target: 99.9%
Step 2 — Create SLO
python3 .harness/methodologies/observability-first/scripts/obs.py \
slo-new refund-availability \
--service "billing-api" \
--sli-good 'sum(rate(refund_request_total{status_code!~"5.."}[5m]))' \
--sli-valid 'sum(rate(refund_request_total[5m]))' \
--target 99.5 \
--window "30d" \
--metric-source "prometheus" \
--description "99.5% of refund requests succeed (no 5xx) over rolling 30d"
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.
- 10d ago First seen · 191 lines · 26 tokens per session scan A 1bdfc002357d
observe-slo is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 1,698 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
capture-feedback
Quick feedback capture with structured signals.
show-lessons
Display promoted lessons and their corrective actions.
harness-review
Review the current change set from an opposing harness-engineering perspective.
step0-specify-feature
Pipeline Step 0 — Specify what you want to build and why, before any technical planning. Surfaces ambiguities early with [NEEDS CLARIFICATION] markers.
harness-doctor
Run Harness Doctor to evaluate how ready the current repository is for reliable AI coding agent collaboration.
harness-update
Update a target repository's harness from the latest harness-starter-kit reference material.