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 CrumbtrailDev/crumbtrail-cli --skill new-path-paritygit clone --depth 1 https://github.com/CrumbtrailDev/crumbtrail-cliWrote 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/crumbtraildev/crumbtrail-cli/new-path-parity)<a href="https://agentmods.dev/skills/crumbtraildev/crumbtrail-cli/new-path-parity"><img src="https://agentmods.dev/badge/skills/crumbtraildev/crumbtrail-cli/new-path-parity.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 | $0.00099 | $0.01991 |
| Opus 5 | $0.00049 | $0.00996 |
| Sonnet 5 | $0.00020 | $0.00398 |
| Haiku 4.5 | $0.00010 | $0.00199 |
Grade A, and why
new-path-parity 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 2d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The new path parity gap
A surface gets reimplemented: a second renderer, a new route, a rewritten editor, a v2 engine behind the same button. The new implementation covers the common cases and quietly drops behaviours the old one had. Parity patches then arrive one property at a time, and the class refills every time a feature lands on the old path only.
The triage question for this archetype is unusual. Before you ask what the bug is, ask which path served the failing action. Everything below is about answering that from a recording.
Symptom
The reporter says the feature works one way and not another: on the old screen but not the new one, on the previous release but not this one, in the classic view but not the rebuilt view. The steps are the same. The data is the same. Only the surface changed.
A second common phrasing: a property the reporter relies on is simply not there any more. No error, no failure, just an option that stopped being honoured.
What Crumbtrail can see
Crumbtrail has no concept of a code path. It records one browsing session at a time and cannot tell you which module, component tree or engine version handled a request. Nothing in a recording says v1 or v2. If a skill told you otherwise it would be wrong.
What a recording does carry, and what makes the comparison possible:
- Navigation events with the exact URL and the transition that produced it, so two runs can be aligned by route.
- Every request and response with method, URL, status, duration and body. Bodies are summarized when large and fields are replaced with a redaction marker when the policy considers them sensitive, so you can rely on the presence and shape of a field more than on its value.
- An environment snapshot taken in the browser: user agent, browser name and version, operating system, viewport, locale and time zone.
- Backend request start, end and error records, but only where the backend SDK is installed.
- Database row changes with the table, the primary key, the before and after column values and a call site file and line, but only where the database adapter is installed.
listSessionsacceptsreleaseandbuildfilters, which is the one place a recording carries a version label at all, and only when the app supplied one.
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.
- 2d ago Changed 5d6d04b630c6
- 6d ago First seen · 175 lines · 99 tokens per session scan A ca59bcd51997
new-path-parity is a skill published in the GitHub repository CrumbtrailDev/crumbtrail-cli (0 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 1,991 once invoked, about $0.0005 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
cce-routing
Use Cursor Bridge's read-only cursorcontextengine for unfamiliar project understanding when the exact code location is unknown or the task requires tracing behavior, symbols, callers and callees, data flow, registrations, interface implementations, ownership boundaries, or cross-module relationships. Trigger for…
gh-fix-ci
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use gh to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
sentry
Query Sentry organizations, projects, and unresolved issues/errors via the Sentry API. Use when the user asks about Sentry errors, issues, or projects.
signoz
Query observability (services, traces, logs, metrics) from a SigNoz instance via its API. Use when the user asks about app performance, errors, latency, or telemetry in SigNoz.
rel-ai-debugging
Use when repository behavior is reproducibly wrong and needs causal diagnosis or repair, including errors, broken tests, crashes, regressions, failed contracts, or incorrect runtime behavior. Do not use for general audits or final verification when no active defect is being diagnosed.
rel-ai-investigation
Use for read-only repository questions that need evidence, including architecture audits, feasibility studies, dependency or caller tracing, impact analysis, implementation-status checks, and proof of how something works. Do not use to implement fixes or for final completion or release verification of changes already…