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 navapbc/digital-service-orchestra --skill fix-cascade-recoverygit clone --depth 1 https://github.com/navapbc/digital-service-orchestraWrote 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/navapbc/digital-service-orchestra/fix-cascade-recovery)<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/fix-cascade-recovery"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/fix-cascade-recovery/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/navapbc/digital-service-orchestra/fix-cascade-recovery"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/fix-cascade-recovery.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 | $0.00149 | $0.01152 |
| Opus 5.5 | $0.00060 | $0.00461 |
| Sonnet 5.5 | $0.00030 | $0.00230 |
| Haiku 4.5 | $0.00015 | $0.00115 |
Grade A, and why
fix-cascade-recovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Cascade Recovery Protocol
Emergency brake fired by the cascade circuit-breaker after 5 cascading failures (CLAUDE.md rule:cascade-circuit). The root cause is rarely where errors appear — read widely, edit narrowly. The fix is usually 1–5 lines once the actual problem is understood.
Prerequisites
Resolve a ticket ID for cascade context, in this order:
- The single open
in_progressticket:.claude/scripts/dso ticket list --status=in_progress --format=llm(most cascades fire mid-task with one in-progress ticket). - None — proceed without ticket comments. The hand-off to
/dso:fix-bugstill works; recovery is not blocked on ticket presence.
Set TICKET_ID for the steps below; if unset or ambiguous (multiple in-progress tickets), skip the ticket comment lines.
Phase A — Recover
Step 1: Assess Damage
Do NOT touch source files. Establish current state:
git diff --stat # blast radius
git diff --name-only # exact files
git log --oneline -10 # last known good
[[ -n "${TICKET_ID:-}" ]] && .claude/scripts/dso ticket show "$TICKET_ID" 2>/dev/null # checkpoint notes
Do NOT re-run the project test suite here — it is known-broken (that's why the breaker fired) and exceeds the 73s tool timeout (CLAUDE.md rule:no-broad-tests-bash, INC-001). The file count from git diff --stat is the load-bearing signal.
If TICKET_ID is set, record file count and original task:
.claude/scripts/dso ticket comment "$TICKET_ID" "Cascade assessment: <N> files changed, original task: <description>"
Step 2: Decide Revert
Decision framework:
- >5 files changed during the cascade → full revert:
git stash --keep-index(preserves for reference; drop after Step 3 confirms a fresh fix is on the way). - Original error was a 1–2 line fix → full revert:
git stash --keep-indexand start fresh. - Some changes correct, others not → selective revert:
git checkout HEAD -- <bad-file>per bad file. Do NOT stash — keep the correct changes in the working tree for the hand-off. - Changes are small and likely all correct → no revert. Do NOT stash. Proceed to Step 3 with the working tree intact.
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.
- 2mo ago First seen · 72 lines · 149 tokens per session scan A dac1ed6312e4
fix-cascade-recovery is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 149 tokens to every session and 1,152 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-03.
fix-cascade-recovery compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fix-cascade-recoverynavapbc/digital-service-orchestra | Skill | 6 | yesterday | Apache-2.0 | A | 149 | Claude Code |
| agent-merge-conflict-arbiterNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 19 | Claude Code, Codex |
| git-advanced-workflowswshobson/agents | Skill | 42k | 2d ago | MIT | A | 54 | Claude Code |
| enable-check-includes-strictchromium/chromium | Skill | 25k | today | BSD-3-Clause | A | 70 | Claude Code, Codex |
| resolve-handoffomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 23 | Claude Code, Codex |
| reproduce-and-fix-issuesbacknotprop/pstack | Skill | 3.9k | yesterday | MIT | A | 48 | Claude Code, Cursor |
| cy-orquestrate-issuecompozy/compozy | Skill | 2.9k | today | MIT | A | 94 | Claude Code, Codex |