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/crumbtraildev/crumbtrail-cli/lying-statusnpx skills add CrumbtrailDev/crumbtrail-cli --skill lying-statusgit 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/lying-status)<a href="https://agentmods.dev/skills/crumbtraildev/crumbtrail-cli/lying-status"><img src="https://agentmods.dev/badge/skills/crumbtraildev/crumbtrail-cli/lying-status.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 | $0.00000 | $0.01904 |
| Opus 5 | $0.00000 | $0.00952 |
| Sonnet 5 | $0.00000 | $0.00381 |
| Haiku 4.5 | $0.00000 | $0.00190 |
Grade A, and why
lying-status 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 4d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The lying status
Status and work travel on different paths. The work is a write, a job, a stream, a sync. The status is a flag, a response code, a progress record, a toast. Nothing makes the two atomic, so whenever the work fails after the status was committed, or the status is computed from something other than the work, the two diverge and the interface reports something that did not happen.
This is the archetype Crumbtrail is strongest on, for a structural reason: the product records the status plane and the work plane separately and can therefore contradict one with the other. Most of the queries below exist to put those two planes side by side.
Symptom
The interface said saved, sent, applied, synced, imported, complete, or showed a green check. The effect is missing, partial, or smaller than reported. Nothing errored.
Variants that are the same archetype: a progress record stuck at in progress with nothing running behind it; an import that reports a row count larger than the rows that exist; a job marked done that left work behind; a response with a success status whose body describes a failure.
What Crumbtrail can see
The status plane and the work plane, and both are ordinary parts of a recording:
- The status plane: response status codes, response bodies, console output, and the interface events around them. Bodies are summarized when large and sensitive fields are replaced with a redaction marker, but a count or a flag in a body normally survives intact.
- The work plane, where the database adapter is installed: row changes with the table, the primary key, the operation, the before and after column values, the request id that caused them and the call site file and line. This is the ground truth a status can be checked against.
- The middle: backend request start, end and error records with the route, the status code and the duration, where the backend SDK is installed. This is what tells you whether the status came from the same process that did or did not do the work.
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.
- 4d ago First seen · 166 lines · 0 tokens per session scan A 4062fa55e1a8
lying-status is a skill published in the GitHub repository CrumbtrailDev/crumbtrail-cli (0 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,904 tokens. 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
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the…