agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Show cost trends across multiple workflow sessions, surfacing expensive operations, spending patterns, and outliers
$ npx -y skills add jmagly/aiwg --skill cost-history --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/cost-historyContext preview
The summary Claude sees to decide when to auto-load this skill.
Show cost trends across multiple workflow sessions, surfacing expensive operations, spending patterns, and outliers
namespace: aiwg name: cost-history platforms: [all] description: Show cost trends across multiple workflow sessions, surfacing expensive operations, spending patterns, and outliers
You show cost trends across multiple workflow sessions. You read historical cost records from `.aiwg/ralph/sessions/` and surface patterns — which operations are expensive, how spending has changed over time, and which sessions were outliers.
For questions about what happened in historical conversations, use `session-explore`. When explaining a cost outlier, correlate the cost record with catalog tool/session evidence only through a reliable identity mapping. Catalog tool-call/result counts and timeline duration are not token usage or billed spend; report an unavailable correlation rather than joining by a similar title.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
| Pattern | Example | Action | |---------|---------|--------| | Full history | "show cost history" | `aiwg cost-history` | | Recent sessions | "last 5 sessions" | `aiwg cost-history --last 5` | | Time window | "costs this week" | `aiwg cost-history --since 7d` | | Trend summary | "are my costs trending up" | `aiwg cost-history --trend` | | Sorted by cost | "most expensive sessions" | `aiwg cost-history --sort cost` |
When triggered:
1. **Determine scope**:
2. **Read session records**:
3. **Compute trend data**:
4. **Run the command**:
# All sessions, newest first aiwg cost-history # Most recent 10 sessions aiwg cost-history --last 10 # Sessions in the past 30 days aiwg cost-history --since 30d # Trend analysis aiwg cost-history --trend # Sorted by cost descending aiwg cost-history --sort cost # JSON output aiwg cost-history --json
Cost History (12 sessions) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Date Session Tokens Cost Status ────────── ────────────────────────── ──────── ────── ────── 2026-04-01 sdlc-review-143022 61,250 $0.18 green 2026-03-31 greenfield-092211 94,800 $0.28 green 2026-03-30 security-review-174503 118,400 $0.36 yellow 2026-03-28 api-development-110022 52,100 $0.15 green 2026-03-26 full-stack-iteration-3 201,700 $0.61 red *outlier ... Totals (12 sessions) Total tokens: 842,100 Total cost: $2.54 Avg/session: $0.21 7-session rolling average: $0.23 Trend: stable (±8% over last 7 sessions)
Cost Trend — Last 7 Sessions Session 6 (oldest): $0.28 Session 5: $0.22 Session 4: $0.36 Session 3: $0.15 Session 2: $0.61 ← outlier (full-stack-iteration-3) Session 1: $0.18 Current avg: $0.23 Direction: stable Outliers: 1 (full-stack-iteration-3 — 2.6x average)
Sessions are color-coded by tokens/line ratio against the MetaGPT 124 tokens/line benchmark (REF-013):
| Status | Tokens/Line | Meaning | |--------|-------------|---------| | green | ≤ 124 | At or below MetaGPT benchmark | | yellow | 125–150 | Above benchmark, acceptable | | red | > 150 | Significantly above benchmark — review recommended |
**User**: "Show cost history"
**Action**:
aiwg cost-history
**Response**: Full session history table with totals, rolling average, and trend direction.
**User**: "What did the last 3 sessions cost?"
**Extraction**: `--last 3`
**Action**:
aiwg cost-history --last 3
**Response**:
Cost History (last 3 sessions) Date Session Tokens Cost ────────── ─────────────────────── ─────── ──── 2026-04-01 sdlc-review-143022 61,250 $0.18 2026-03-31 greenfield-092211 94,800 $0.28 2026-03-30 security-review-174503 118,400 $0.36 Total: $0.82 over 3 sessions (avg: $0.27)
**User**: "Which sessions were most expensive?"
**Action**:
aiwg cost-history --sort cost
**Response**: History table sorted by cost descending, with outlier flag on sessions more than 2x the rolling average.
If a time window is ambiguous:
Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.
Repo: jmagly/aiwg
Crash-resilient external agent loop with state persistence and CI/CD integration
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Enable agent loops to learn from similar past tasks and share patterns across loops
Query and manage the executable feedback debug memory
Execute tests on generated code and iterate until passing