Przejdź do treści
Biblioteka skilli
AI i agenci · Przegląd i audyt

harness-observability

/harness-observability

Sprawdza zdrowie harnessu agenta, konfiguruje cykliczne przeglądy, eksport telemetrii i format migawek.

Licencja
Apache-2.0
Ostatnia zmiana repozytorium
19.10.2026

Ocena i bezpieczeństwo

90/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść25 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
5
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 19.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

Co robi i kiedy

Sprawdza zdrowie harnessu agenta, konfiguruje cykliczne przeglądy, eksport telemetrii i format migawek.

Oryginalny opis (EN)

Use when checking harness health, setting up observability cadences, understanding snapshot formats, configuring telemetry export, or verifying that the harness's own observability is working — covers all four layers of harness observability

Jak działa

  1. The Four Layers
  2. Layer 1: Operational Cadence
  3. Layer 2: Trend Visibility
  4. Layer 3: Telemetry Export
  5. Layer 4: Meta-Observability
  6. When to Use This Skill
  7. README Health Indicator
Sekcje z nagłówków SKILL.md, w oryginale · 137 linii, 816 słów
Podgląd SKILL.md
---
name: harness-observability
description: Use when checking harness health, setting up observability cadences, understanding snapshot formats, configuring telemetry export, or verifying that the harness's own observability is working — covers all four layers of harness observability
---

# Harness Observability

Harness observability is the measurement layer that makes context
engineering, architectural constraints, and garbage collection
evidence-based rather than intuition-based. Without it, a harness is
infrastructure you hope works. With it, you know.

This skill covers four layers of observability, each answering a
different question at a different timescale.

This skill does not cover CI workflow configuration (middle loop),
individual constraint design, or garbage collection rule authoring —
those belong to their respective skills. It covers how to observe
whether those mechanisms are operating effectively.

For the snapshot schema and field definitions, consult
`references/snapshot-format.md`. The snapshot includes a Diaboli panel
(after Session Quality, before Operational Cadence) that surfaces
advocatus-diaboli activity as descriptive stats across all objection records.

## The Four Layers

| Layer | Question | Timescale | Consumer |
| ------- | ---------- | ----------- | ---------- |
| Operational Cadence | "Is the harness running?" | Session / weekly / quarterly | Developer in session |
| Trend Visibility | "How has the harness changed?" | Weekly / quarterly | Team over time |
| Telemetry Export | "Can I visualise this externally?" | Continuous | External dashboards |
| Meta-Observability | "Is the observability itself working?" | Quarterly | Agents + team |

## Layer 1: Operational Cadence

The harness has mechanisms — audit, GC, reflection, mutation testing —
but mechanisms only work if they run. Operational cadence ensures they
actually fire on schedule.

**The primary tool is `/harness-health`.** Running it:

1. Produces a structured snapshot of the harness's current state
2. Surfaces deltas from the previous snapshot
3. Flags overdue cadences (e.g. "last audit was 45 days ago")
4. Updates the README health badge

**Recommended cadences:**

| Mechanism | Cadence | Command |
| ----------- | --------- | --------- |
| Health snapshot | Monthly | `/harness-health` |
| Full audit | Quarterly | `/harness-audit` |
| Assessment | Quarterly | `/assess` |
| Reflection review | Quarterly | Review REFLECTION_LOG.md |
| Mutation trend check | Monthly | Download CI artifacts |

A Stop hook nudges the developer when the last snapshot is older than
30 days. This turns a declared cadence into an actual practice.

## Layer 2: Trend Visibility

Snapshots are point-in-time. Trends are the delta between snapshots.
No external tooling required — trends are computed by diffing markdown
files.

When `/harness-health` runs and a previous snapshot exists, it:

1. Computes deltas for every tracked metric
2. Appends a Trends section to the new snapshot
3. Prints a delta summary to the session

For quarterly reviews, `/harness-health --trends` reads all snapshots
and produces a multi-period trend view.

**What agents do with trends:** The orchestrator reads the latest
snapshot's Trends section before planning work. Declining mutation
scores might trigger test quality prioritisation. A stalled learning
flow might prompt a `/reflect` nudge.

## Layer 3: Telemetry Export

For teams that want Grafana, Langfuse, or other external dashboards,
the snapshot data can be exported as OpenTelemetry metrics.

This is optional. The file-based approach (Layers 1-2) works without
any external tooling. Telemetry export adds continuous visibility for
teams operating at scale.

For OTel metric names, semantic conventions, and a reference export
script, consult `references/telemetry-export.md`.

## Layer 4: Meta-Observability

The self-referential layer: the harness checking whether its own
observability is working.

"A harness that cannot verify its own operation is a harness you hope
works."

The harness-auditor agent runs five meta-checks:

| Check | Signal |
| ------- | -------- |
| Snapshot currency | Stale = outer loop not running |
| Cadence compliance | Overdue = practice not followed |
| Learning flow | Stalled = compound learning broken |
| GC effectiveness | Silent = rules may be misconfigured |
| Trend direction | Unacknowledged decline = drift unnoticed |

For thresholds and detailed check definitions, consult
`references/meta-observability-checks.md`.

## When to Use This Skill

| Situation | Action |
| ----------- | -------- |
| Starting a new quarter | Run `/harness-health` to baseline |
| After a major feature lands | Run `/harness-health` to check impact |
| Harness feels stale | Run `/harness-health --deep` for authoritative check |
| Quarterly review | Run `/harness-health --trends` for multi-period view |
| Setting up a new project | Configure cadences in CLAUDE.md |
| Want external dashboards | Follow `references/telemetry-export.md` |

## README Health Indicator

`/harness-health` maintains two README elements:

**Health badge** — shields.io, colour-coded:

| Status | Condition | Colour |
| -------- | ----------- | -------- |
| Healthy | All layers operating, no overdue cadences | Green |
| Attention | One layer degraded or outer loop overdue | Amber |
| Degraded | Multiple layers degraded or no snapshot in 30+ days | Red |

**Health icon** — a custom SVG linked to the latest snapshot.

The badge colour factors in meta-health. Stale snapshots or overdue
cadence trigger amber even if enforcement ratios look fine.
Pliki w paczce (5)
  • SKILL.md 5 KB
  • references/meta-observability-checks.md 5 KB
  • references/observatory-signals.md 7 KB
  • references/snapshot-format.md 19 KB
  • references/telemetry-export.md 6 KB

Wersje

W bazie nie ma innych skilli o nazwie harness-observability.

Migawka bazy z 13.11.2026 · wersja paczki 43ff33fc8f1d (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 90harness-observatory
    Buduje lokalny panel obserwacji sesji agentów z logów Claude Code i Codex oraz proponuje poprawki CLAUDE.md i AGENTS.md.
  • 95configure-harness
    Konfiguruje, które harnessy agentów uruchamia octomux: model dla zadania, wybór harnessu, ustawienia i rejestrację dodatkowych przez wtyczkę.
  • 90harness-audit-engine
    Wykrywa dryf konfiguracji harnessu agenta: pliki konwencji, ONBOARDING, nieaktualne migawki i regresje ograniczeń.
  • 95observability
    Konfiguruje obserwowalność agentów AI: ślady, ewaluacje, eksperymenty A/B i zbieranie opinii o odpowiedziach.
  • 90harness-setup
    Inicjalizuje albo aktualizuje konfigurację Oh My Harness w projekcie Codex.
  • 90coding-agent-harness
    Projektuje harness agenta kodującego: ograniczenia, weryfikację i bazę akceptacji oraz ocenia, które zadania nadają się dla agenta.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.