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 marcusgoll/Spec-Flow --skill error-recoverygit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote 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/marcusgoll/spec-flow/error-recovery)<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/error-recovery"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/error-recovery.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 5.1 | $0.00034 | $0.01932 |
| Opus 5 | $0.00017 | $0.00966 |
| Sonnet 5 | $0.00007 | $0.00386 |
| Haiku 4.5 | $0.00003 | $0.00193 |
Grade C, and why
error-recovery scanned grade C 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .next .cache coverage node_modules/.cache dist build How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill when:
- Sprint fails during /implement-epic
- Feature fails during /implement
- Quality gate blocks deployment
- Any workflow phase returns FAILED status
<quick_start> When a workflow component fails:
- Classify the failure using the decision tree below
- If fixable: Execute auto-fix strategies (max 3 attempts)
- If critical: Stop immediately, report to user
- If unknown: Treat as critical (safe default)
Classification determines whether workflow can auto-recover or requires user intervention. </quick_start>
<failure_classification>
Critical Blockers (MUST STOP)
These failures require manual intervention - never auto-retry:
| Failure Type | Detection | Why Critical |
|---|---|---|
| CI Pipeline | ci_pipeline_failed: true in state.yaml |
GitHub Actions/GitLab CI failed - indicates code issue |
| Security Scan | security_scan_failed: true |
High/Critical CVEs found - security risk |
| Deployment | deployment_failed: true |
Production/staging crashed - user-facing impact |
| Contract Violation | contract_violations > 0 |
API contract broken - breaks consumers |
Action: Stop workflow, report error details, require /continue after manual fix.
Fixable Issues (CAN AUTO-RETRY)
These failures often resolve with automated fixes:
| Failure Type | Detection | Auto-Fix Strategies |
|---|---|---|
| Test Failures | tests_failed: true (no CI failure) |
re-run-tests, check-dependencies |
| Build Failures | build_failed: true |
clear-cache, reinstall-deps, rebuild |
| Dependency Issues | dependencies_failed: true |
clean-install, clear-lockfile |
| Infrastructure | infrastructure_issues: true |
restart-services, check-ports |
| Type Errors | type_check_failed: true |
(manual fix usually required) |
Action: Attempt auto-fix strategies (max 3 attempts), then escalate if all fail.
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.
- 4d ago First seen · 276 lines · 34 tokens per session scan C 5f3238998b6f
error-recovery is a skill published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,932 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
qa
Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
clash-resolution-analyzer
Analyze BIM clash detection results and suggest resolutions. Prioritize clashes, identify patterns, assign responsibility, and track resolution status.
bugherd-automation
Automate Bugherd tasks via Rube MCP (Composio). Always search tools first for current schemas.
worker
Team worker protocol (ACK, mailbox, task lifecycle) for tmux-based OMX teams.
incident-learning
Convert operational incident and near-miss evidence into durable product, engineering, test, evaluation, and governance improvements with verified closure. Separate observed facts from causal hypotheses and unresolved uncertainty; map follow-up work across code, tests, skills, operations, product, and governance…