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 | $0.00075 | $0.00576 |
| Sonnet 5 | $0.00030 | $0.00230 |
| Haiku 4.5 | $0.00015 | $0.00115 |
Grade A, and why
fix-cascade-recovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Cascade Recovery Protocol
Emergency brake fired by the cascade circuit-breaker after 5 cascading failures (CLAUDE.md rule:cascade-circuit). The root cause is rarely where errors appear — read widely, edit narrowly. The fix is usually 1–5 lines once the actual problem is understood.
Prerequisites
Resolve a ticket ID for cascade context, in this order:
- The single open
in_progressticket:.claude/scripts/dso ticket list --status=in_progress --format=llm(most cascades fire mid-task with one in-progress ticket). - None — proceed without ticket comments. The hand-off to
/dso:fix-bugstill works; recovery is not blocked on ticket presence.
Set TICKET_ID for the steps below; if unset or ambiguous (multiple in-progress tickets), skip the ticket comment lines.
Phase A — Recover
Step 1: Assess Damage
Do NOT touch source files. Establish current state:
git diff --stat # blast radius
git diff --name-only # exact files
git log --oneline -10 # last known good
[[ -n "${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.
- 9d 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 $0.0007 per session on Opus 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.
Other skills, from other repositories
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.
mantis-critic
Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for writing reproduction scripts or patches.
hotpath_bump
Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…
cy-orquestrate-issue
Orchestrate GitHub bug resolution through a new CompozyOS managed worktree and Codex Astra High session per issue. Investigate reported bugs, create missing issues, and dispatch a Goal-backed executor responsible for a detailed PR, green CI, and all CodeRabbit and Greptile feedback. Use when asked to delegate issue…