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 unowned-contractgit 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/unowned-contract)<a href="https://agentmods.dev/skills/crumbtraildev/crumbtrail-cli/unowned-contract"><img src="https://agentmods.dev/badge/skills/crumbtraildev/crumbtrail-cli/unowned-contract.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 | $0.00081 | $0.01555 |
| Opus 5 | $0.00041 | $0.00777 |
| Sonnet 5 | $0.00016 | $0.00311 |
| Haiku 4.5 | $0.00008 | $0.00155 |
Grade A, and why
unowned-contract 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 3d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The wrapped thing changed seam
Somebody else's contract moved. A vendor API, a firmware build, a warehouse dialect, a model provider: whatever the adapter wrapped changed its payload, its authentication or its meaning out of band, and the adapter that trusted the old shape broke. The fix is almost always to handle the new shape, not to restore the old behaviour.
Symptom
An integration that has worked for a long time starts failing, and nothing shipped on our side. Or the call still succeeds and the data it carries no longer matches what the code reads: a field that is now absent, a type that flipped, an identifier that is now a string, a list that became an object.
Authentication is the other common face of it. Requests that used to be accepted now come back as a redirect, a login page, or a rejection with a shape the adapter does not recognise.
What Crumbtrail can see
For every request the browser made, including calls to external hosts, a session carries the
method, the URL, the status, the timing, the headers when header capture is enabled, and the
request and response bodies subject to the capture size limit and the redaction policy. Where the
backend integration is installed, backend spans carry the same for calls that integration
instruments, and a response body when it reports one. getLinkedRequestContext returns the
joined frontend and backend view of one request id.
Several named detector signals point straight at this archetype when they fire:
content_type_body_mismatch, api_route_returned_document (a document arriving where structured
data was expected, which is what an expired session or a moved authentication endpoint looks
like), response_count_mismatch, backend_http_error,
backend_http_client_error and invalid_webhook_signature_accepted.
It does not see a call your backend makes to a vendor unless the backend integration is installed and instruments that call. It does not see the vendor's changelog, deprecation notice or status page, and it never will, because none of that is in the running application. A body larger than the configured maximum is summarised rather than stored, and fields the redaction policy classifies as sensitive are replaced with non recoverable shape metadata. When the field that changed is a redacted one you can see that its shape moved and you cannot see its value.
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.
- 3d ago Changed cf4374e81511
- 7d ago First seen · 144 lines · 81 tokens per session scan A 46ac0d8a335a
unowned-contract is a skill published in the GitHub repository CrumbtrailDev/crumbtrail-cli (0 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 1,555 once invoked, about $0.0004 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…