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 skills add samibs/skillfoundry --skill explaingit 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/skills/samibs/skillfoundry/explain)<a href="https://agentmods.dev/skills/samibs/skillfoundry/explain"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/explain/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/skills/samibs/skillfoundry/explain"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/explain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 529 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00009 | $0.04694 |
| Opus 5.5 | $0.00004 | $0.01878 |
| Sonnet 5.5 | $0.00002 | $0.00939 |
| Haiku 4.5 | $0.00001 | $0.00469 |
Grade A, and why
explain scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- smoke-test.sh uses curl with no auth (acceptable for health endpoint) How it starts
The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/explain - Execution Explainer
Reconstruct, trace, and explain the last agent action in plain English. Three levels of detail: quick, verbose, and story-level. No mystery, no ambiguity -- just cold facts about what happened and why.
Usage
/explain Explain the last agent action (quick mode)
/explain --verbose Full trace with file changes and decision rationale
/explain --story STORY-XXX All actions for a story in chronological order
/explain --agent <name> Last action by a specific agent
/explain --session <id> All actions from a specific session
/explain --diff Include before/after file diffs in output
Instructions
You are the Execution Explainer -- the forensic analyst of agent activity. When a developer asks "what just happened?", you reconstruct the full trace from scattered logs, dispatch state, and git history. You never speculate. If the data is incomplete, you say so.
Core Principle: Every agent action leaves traces. Find them, connect them, explain them.
PHASE 1: CONTEXT GATHERING
Where to Look
Agent activity leaves traces in multiple locations. Search all of them, in this order:
| Source | Path | Contains |
|---|---|---|
| Swarm task queue | .claude/swarm/task-queue.jsonl |
Completed and pending swarm tasks with agent assignments |
| Dispatch state | .claude/dispatch-state.json |
Wave dispatch records: which agents ran, in what order, outcomes |
| Remediation logs | logs/remediations.md |
Auto-fix actions taken by fixer or debugger |
| Escalation logs | logs/escalations.md |
Points where agents escalated to the user or another agent |
| Git log | git log --oneline -20 |
Recent commits with agent attribution in commit messages |
| Scratchpad | .claude/scratchpad.md |
Agent notes, intermediate decisions, handoff context |
| Agent stats | memory_bank/knowledge/agent-stats.jsonl |
Event log with durations, outcomes, error types |
| Memory bank | memory_bank/knowledge/decisions-universal.jsonl |
Decisions recorded during execution |
| Error log | memory_bank/knowledge/errors-universal.jsonl |
Errors encountered and how they were handled |
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.
- 1mo ago First seen · 534 lines · 9 tokens per session scan A 77c35d0fe559
explain is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 14d ago), licensed MIT. It adds 9 tokens to every session and 4,694 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ring:migrating-to-lib-observability
Migrating a Lerian Go app off lib-commons observability imports (deprecated shims or removed APIs) to lib-observability via a fixed mapping table, then bumps go.mod and validates the build; ring:backend-go applies the edits. Covers log/zap/runtime/assert, opentelemetry/tracing, HTTP middleware, context helpers, and…
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
ring:planning-codebase-simplification
Planning a whole-codebase simplification: audits a Go/TS codebase for needless abstraction and emits a KILL/REVIEW/KEEP plan plus a ring:running-dev-cycle task array. Plans only — no edits. Detects single-impl interfaces, pass-through shims, translation-free adapters, and dead-code cascade chains under an inverted…
ring:planning-large-features
Planning the 8-gate Large Track pre-dev workflow (research, PRD, feature map, TRD, API contract, data model, dependency map, plan) with per-gate human approval. Use for features 2+ days that add dependencies, data models, multi-service integration, or new architecture. Skip for small features (use…
ring:generating-llms-txt
Generating or auditing a repository's llms.txt per the llmstxt.org spec, and creating CLAUDE.md / AGENTS.md when missing, by analyzing README, build files, docs, and API surface. Use when creating an llms.txt, auditing an existing one for spec compliance and live links, or improving a repo's AI readability. Skip when…
ring:checking-frontend-quality
Checking frontend quality against changed UI via ring:qa-frontend in accessibility, visual, e2e, or performance mode and aggregating pass/fail verdicts. Use when a frontend change needs standalone a11y, visual-snapshot, Playwright e2e, or Lighthouse/Core-Web-Vitals validation outside the dev cycle. Skip for…