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 env-promotiongit 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/env-promotion)<a href="https://agentmods.dev/skills/crumbtraildev/crumbtrail-cli/env-promotion"><img src="https://agentmods.dev/badge/skills/crumbtraildev/crumbtrail-cli/env-promotion.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 | $0.00094 | $0.01789 |
| Opus 5 | $0.00047 | $0.00894 |
| Sonnet 5 | $0.00019 | $0.00358 |
| Haiku 4.5 | $0.00009 | $0.00179 |
Grade A, and why
env-promotion 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The environment to environment promotion blind spot
A promotion tool moves objects between environments by matching on name and exact structure. When the two environments have drifted, when a name is duplicated, when a sub object is unsupported, or when something was renamed, the comparator breaks. The worse case is that it does not break: it reports success, and the payload arrives incomplete or mangled.
Read the limits section of this skill before running the queries. More of this archetype lives outside the recording than in any other archetype in this collection, and the honest answer is often that the recording characterises the damage while the cause is confirmed elsewhere.
Symptom
Something that works in one environment fails in the next after a promotion. An object arrives missing its dependencies. A configuration import reports success and the target is short. A comparator reports a difference that does not exist, or reports none where there is one. Users in the promoted environment see a feature behave differently from the one it was copied from.
What Crumbtrail can see
Whatever the application did in the target environment, if capture was running there. That is requests and responses with status, timing and body, console errors and unhandled rejections, navigation, storage and cookie changes, backend spans where the backend integration is installed, and database row changes where the database adapter is installed. Together those characterise the target failure precisely enough to name the object that is missing or wrong.
Environment identity is available in two forms, both of which are opt in. The application can
declare a release label, a build label and arbitrary configuration to the SDK, which is where an
environment name lives when a team puts it there. Separately, a session created automatically from
backend telemetry takes its identity from the reporting service's resource attributes, so when
deployment.environment is set on that service the environment name is part of the session
identity. Check which of these your deployment uses before assuming either.
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 · 162 lines · 94 tokens per session scan A 8ebf481b977b
env-promotion is a skill published in the GitHub repository CrumbtrailDev/crumbtrail-cli (0 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,789 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 the GitHub app from this plugin for PR metadata and patch context, and use gh for Actions check and log inspection before implementing any approved fix.
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…
fix-default
A default procedure for handling bug fixes, organised as a three-step scan and a CP process. The input does not explain what the three steps or CP process contain.
repair-prevention-assessment
A completion gate for fixes and self-repair work. It creates a machine-checkable assessment that separates evidence a current issue is closed from evidence that the fix will remain effective.