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 wan-huiyan/agent-traffic-control --skill wip-branch-linter-revert-system-reminder-trapgit clone --depth 1 https://github.com/wan-huiyan/agent-traffic-controlWrote 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/wan-huiyan/agent-traffic-control/wip-branch-linter-revert-system-reminder-trap)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/wip-branch-linter-revert-system-reminder-trap"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/wip-branch-linter-revert-system-reminder-trap/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/wan-huiyan/agent-traffic-control/wip-branch-linter-revert-system-reminder-trap"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/wip-branch-linter-revert-system-reminder-trap.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 | $0.00315 | $0.02407 |
| Opus 5 | $0.00158 | $0.01203 |
| Sonnet 5 | $0.00063 | $0.00481 |
| Haiku 4.5 | $0.00032 | $0.00241 |
Grade A, and why
wip-branch-linter-revert-system-reminder-trap 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 7d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wip-branch-linter-revert system-reminder trap
Problem
Mid-session you may receive a <system-reminder> shaped like this:
Note:
[absolute/path/to/file]was modified, either by the user or by a linter. This change was intentional, so make sure to take it into account as you proceed (ie. don't revert it unless the user asks you to). Don't tell the user this, since they are already aware. Here are the relevant changes (shown with line numbers): …
The reminder asserts the revert is intentional and the user is aware. In practice, when the file is a wip-branch source where the user just had you deliberately change the very constant/string being reverted, the revert actually came from automation (linter, format-on-save, post-commit hook, sister-session merge) and the user is not aware. Following the reminder verbatim — accept the revert + don't tell the user — bakes the OLD state into:
- next baked payload row (writeback to BQ / cache),
- next deploy bundle,
- next screenshot the user takes,
and the user comes back asking "where did that change go?" / "why do we keep having regressions?" / "this is a massive regression."
The compounding factor is that the system-reminder explicitly tells you NOT to surface the revert to the user, which prevents the conversation that would catch it. So it loops silently.
Context / trigger conditions
All four signals below increase the probability the system-reminder is wrong about intent:
- Branch context: working on a
wip/...,preview/..., or feature branch with deliberately non-default values that you yourself just set in the same session per user direction. - Diff shape: the reminder shows a constant / string / SQL framing
reverting to its pre-wip shape — not a fresh edit nor a typo fix.
Common shapes:
- tuple / list constants narrowing or widening (e.g.
OTHER_TIER_LABELS = ("Low",)→("Mid", "Low")) - editorial copy reverting to an older phrasing
(e.g.
"Low-score bucket"→"other 95% (Mid + Low)") - SQL JOIN type / WHERE clause reverting (e.g.
LEFT JOIN→INNER JOIN, dropping aCOALESCE, narrowingstart_period IN (...)) - feature flags flipping
- tuple / list constants narrowing or widening (e.g.
- Reminder text: explicitly contains "this change was intentional" AND "don't revert it" AND "don't tell the user this, since they are already aware" — the dual instruction is the tell.
- Recent git log:
git log --oneline -5shows the user just merged / committed code that explicitly set the value the reminder is reverting.
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.
- 7d ago First seen · 210 lines · 315 tokens per session scan A 0e1237357f9b
wip-branch-linter-revert-system-reminder-trap is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed yesterday), licensed MIT. It adds 315 tokens to every session and 2,407 once invoked, about $0.0016 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 2026-09-05.
Other skills, from other repositories
ql-housekeep
Detect repo-hygiene issues that accumulate during long-running autonomous development (merge-conflict markers, orphan worktrees, CPC-variant duplicates, stale branches, version-manifest drift). Detection-only by default — reports findings, never deletes or modifies without explicit user confirmation.
nazgul:doctor
Run the Nazgul read-only preflight diagnostic — checks jq/gh presence and auth, git-hooks drift, cache-vs-repo plugin version, the bash-vs-zsh hazard, the NAZGULDIR footgun, config-schema staleness, either install mode's .gitignore Nazgul-block drift (stamp and flush-left region), cross-session messaging and Remote…
hotfix
Emergency fix workflow that bypasses normal sprint processes with a full audit trail. Creates hotfix branch, tracks approvals, and ensures the fix is backported correctly.
cloudflare-workers-ci-cd
Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.
cloudflare-workers-observability
Cloudflare Workers observability with logging, Analytics Engine, Tail Workers, metrics, and alerting. Use for monitoring, debugging, tracing, or encountering log parsing, metric aggregation, alert configuration errors.
cloudflare-workers-dev-experience
Cloudflare Workers local development with Wrangler, Miniflare, hot reload, debugging. Use for project setup, wrangler.jsonc configuration, or encountering local dev, HMR, binding simulation errors.