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 format-boundarygit 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/format-boundary)<a href="https://agentmods.dev/skills/crumbtraildev/crumbtrail-cli/format-boundary"><img src="https://agentmods.dev/badge/skills/crumbtraildev/crumbtrail-cli/format-boundary/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/crumbtraildev/crumbtrail-cli/format-boundary"><img src="https://agentmods.dev/badge/skills/crumbtraildev/crumbtrail-cli/format-boundary.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 | $0.00000 | $0.01808 |
| Opus 5.5 | $0.00000 | $0.00723 |
| Sonnet 5.5 | $0.00000 | $0.00362 |
| Haiku 4.5 | $0.00000 | $0.00181 |
Grade A, and why
format-boundary 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 1mo 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The timezone, locale or format boundary
A value is written in one context and read in another. The contexts disagree about a default: which zone a naive timestamp belongs to, which day a week starts on, whether a comma is a thousands separator or a decimal point, how many minor units a currency has, which calendar or numeral system the locale implies. The value survives the trip and its meaning does not.
Two properties make this family expensive. It clusters at midnight, at daylight saving transitions, at month and quarter ends, so it looks intermittent while being entirely deterministic. And it is a family rather than a site: fixing the one place a reporter noticed leaves every sibling untouched, which is why the same defect returns under a different label.
Symptom
A date is off by one day, or by exactly the offset between two zones. A report attributed to the wrong period at a boundary. A number rendered with the wrong separator, or a total out by a factor of a hundred. A week that starts on the wrong day. A duration or a unit shown in the wrong scale.
The strongest clue in the report itself is that the same value is correct somewhere else in the product. One representation is right and another is wrong.
What Crumbtrail can see
The most useful fact for this archetype comes free and is easy to miss. A recording carries an environment snapshot taken in the browser, and the ranked bundle exposes it as an environment block holding the user agent, the browser, the operating system, the viewport, the locale and the time zone the session ran under. That is the reporter's context, which is the thing you would otherwise have to ask for and would usually get wrong.
Beyond that, the point of the recording here is that the same value appears in several representations and you can compare them:
- The request body, holding the value as the browser serialized it.
- The response body, holding it as the server serialized it. Bodies are summarized when large and sensitive fields are replaced with a redaction marker.
- The stored row, where the database adapter is installed, holding the value as the column actually contains it, with the before and after of any change.
- Backend request records with routes and durations, where the backend SDK is installed.
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.
- 1mo ago First seen · 163 lines · 0 tokens per session scan A db9bb7288ff2
format-boundary is a skill published in the GitHub repository CrumbtrailDev/crumbtrail-cli (0 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,808 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
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
memory-leak-debug
Diagnose memory leaks in the Qwen Code CLI using heap snapshots and the chrome-devtools CLI. Use when investigating high memory usage, unbounded growth, or suspected object retention issues.
bugfix
Fix a bug from a GitHub issue, following the reproduce-first workflow. Use when the user asks to fix a bug, investigate a GitHub issue, or debug a user-reported problem. Takes a GitHub issue URL or number as input.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.