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 agentmods add skills/everywan-dev/claude-code-engineering/survive-someone-elses-breaking-changenpx skills add everywan-dev/claude-code-engineering --skill survive-someone-elses-breaking-changegit clone --depth 1 https://github.com/everywan-dev/claude-code-engineeringWrote 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/everywan-dev/claude-code-engineering/survive-someone-elses-breaking-change)<a href="https://agentmods.dev/skills/everywan-dev/claude-code-engineering/survive-someone-elses-breaking-change"><img src="https://agentmods.dev/badge/skills/everywan-dev/claude-code-engineering/survive-someone-elses-breaking-change.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 | $0.00043 | $0.01128 |
| Opus 5 | $0.00022 | $0.00564 |
| Sonnet 5 | $0.00009 | $0.00226 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
survive-someone-elses-breaking-change 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 6d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Survive someone else's breaking change
"We changed nothing" is usually true and never relevant. You are standing on a stack of other people's decisions, and any of them can move.
The distinctive feature of this failure class is that the error message describes your side, not theirs. You get a 404, a cryptic code, an empty result — symptoms of your own request being wrong, when what changed is what the other side accepts.
🔴 When something breaks with no change on your side, stop debugging your code and start dating the change. What moved, and when? That question resolves this class of incident faster than any amount of reading your own diff.
When to use this
- It worked yesterday, nothing was deployed, it fails today
- After any upgrade: dependency, runtime, base image, platform, browser
- An error code you have never seen and cannot find documented
- A vendor announced a deprecation and you are not sure it affects you
- You are about to change something other people consume
Diagnosing it
1. Establish what moved, with a timestamp. Deployment logs, image digests, package lockfile diffs, the vendor's changelog and status page, an auto-update you forgot was enabled. Something has a new date on it.
2. Suspect the negotiated layer. Most of these live where two sides agree on a version at runtime: API versions, protocol versions, TLS versions, feature flags, image tags that moved. Both sides are individually correct; the negotiation is what broke.
3. Reproduce with the old and new version side by side. One variable. If you cannot pin the old version to compare, that is the first thing to fix, and it is also the answer to how you avoid the next one.
4. Search for the symptom, not the cause, and expand the search. If there is nothing on the internet about your error, consider that you may be in a rare configuration — an old setting, a fossil default, something inherited from a migration. Rare configurations are where undocumented breakage lives.
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.
- 6d ago First seen · 101 lines · 43 tokens per session scan A 63ca0443c074
survive-someone-elses-breaking-change is a skill published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,128 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
wiki-lint
Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…
debug
Systematic 4-phase debugging with escalation protocol. Use when saying "debug", "investigate bug", "find root cause", "why is this failing", or "fix this bug".
dead-code-cleanup
Use when the user asks about cleanup, removing unused code, refactoring, reducing bundle size, or identifying dead code in a Repowise-indexed codebase (.repowise/ directory exists). Also activates when discussing technical debt, code hygiene, or repository maintenance.
analyze-codebase
Run a multi-agent deep analysis of a codebase, producing AI-readable analysis documents in .ai/docs/ covering structure, dependencies, data flow, request flow, and APIs. Use whenever the user asks to analyze a repository, generate codebase analysis, understand an unfamiliar codebase in depth, or before generating…
raytsystem-lint
Run deterministic integrity, provenance, projection, link, alias, operation, and secret checks over raytsystem. Use for LINT, health checks, pre-commit verification, stale projection diagnosis, broken evidence, or semantic review; never auto-fix canonical knowledge.
rca
Root-cause analysis for code. Use when a defect shipped and was caught after the fact, a run came back BLOCKED or a deliverable failed validation, a bug recurs after a prior fix, or the user says 'rca this', 'root cause this', 'postmortem this', or 'why did this break'. Produces a structured RCA that separates surface…