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 suryast/free-ai-agent-skills --skill approval-blocked-maintenance-loopsgit clone --depth 1 https://github.com/suryast/free-ai-agent-skillsWrote 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/suryast/free-ai-agent-skills/approval-blocked-maintenance-loops)<a href="https://agentmods.dev/skills/suryast/free-ai-agent-skills/approval-blocked-maintenance-loops"><img src="https://agentmods.dev/badge/skills/suryast/free-ai-agent-skills/approval-blocked-maintenance-loops/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/suryast/free-ai-agent-skills/approval-blocked-maintenance-loops"><img src="https://agentmods.dev/badge/skills/suryast/free-ai-agent-skills/approval-blocked-maintenance-loops.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 | $0.00044 | $0.00822 |
| Opus 5.5 | $0.00018 | $0.00329 |
| Sonnet 5.5 | $0.00009 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
approval-blocked-maintenance-loops 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 5d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Approval-blocked maintenance loops
Classify before retrying
| State | Meaning | Next decision |
|---|---|---|
awaiting_approval |
The actual approval prompt is still open | Wait; do not create another prompt |
denied |
Operator declined the named operation | Retain checkpoint; request changed scope once, not each wakeup |
expired |
Prompt timed out or closed without consent | Record no approval; automatic wakeups cannot renew it |
unknown |
Request was sent but outcome is ambiguous | Hold writes; reconcile through independently authorized read-back |
transient_failure |
Evidence proves no side effect occurred; a temporary failure is classified | Retry only within existing consent and bounded retry budget |
ready |
Explicit scope approval and prerequisites are current | Make one approved attempt, then verify |
completed |
Exact intended result was independently read back | Clear only the matching blocker |
A transport timeout after dispatch is unknown, not automatically transient. A retry may duplicate an action. A user message asking to continue may authorize one scoped approval attempt, but cannot replace a tool's approval interface. Track separate approval domains independently.
Persist one bounded checkpoint
Record operation ID, exact target/action, scope exclusions, state, last known execution evidence, completed deliverables, verification method, retry count/budget, operator decision requested, and the event needed to resume. Use non-secret artifact references rather than full logs, credentials, private payloads, or unlimited histories. Set retention/size limits and atomically replace the checkpoint using the runtime's supported storage. See synthetic checkpoint.
At each scheduled wakeup:
- Read the saved checkpoint; do not redispatch or reopen prompts merely because the clock fired.
- Consider only new consent, changed prerequisites, or an explicitly required independently authorized read. A status check is not implementation progress. Never obtain a denied outcome through another tool, command, endpoint, or delegate.
- Advance unrelated, independently authorized work only within its own scope; propagate denials to delegates. Do not bundle independent diagnostics with gated mutations.
- Once independent work is exhausted, request the operator decision once: retry the exact named operation through normal approval, revise scope, or authorize a supported pause. Remain blocked if no answer arrives; never mark an unfinished task complete to stop a loop.
- On approved resume, refresh source and uncommitted deliverables, verify target/scope, perform only the approved step, then read back the exact result. Clear stale blocker labels immediately after verified success. If approval expires again, return to the checkpoint rather than retrying on the next wakeup.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 49 lines · 44 tokens per session scan A 933c647e5852
approval-blocked-maintenance-loops is a skill published in the GitHub repository suryast/free-ai-agent-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 44 tokens to every session and 822 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
concierge
Use when a task needs the judgment of a Concierge — securing a reservation at a fully-booked restaurant or sold-out venue, coordinating a multi-vendor guest request (dinner, transportation, and a gift delivery) inside a tight window, deciding when to pivot from a failed Plan A to a same-caliber Plan B, or navigating a…
correspondence-clerk
Use when a task needs the judgment of a Correspondence Clerk — selecting and customizing a template response to a standardized written inquiry, triaging a correspondence queue against SLA deadlines, deciding when a form letter suffices versus needs escalation, or auditing a response-template library for staleness.
chief-of-staff
Pursue a long-running goal in a single session by co-ordinating subagents.
bash
Expert Bash shell scripting assistance covering POSIX compliance, parameter expansion, pipelines, traps, and debugging. Use when writing robust shell scripts, automating DevOps tasks, or handling file processing.
telegram-agent
Telegram CLI for AI agents. Use when the user needs to read or search Telegram, send or edit a message, download media, organise Saved Messages, monitor conversations, or automate a Telegram task. Triggers on “check my messages”, “send a message”, “search Telegram”, “read unread”, “listen to chat”, “download from…
token-guard
Use Codex Token Guard to reduce noisy command and tool-output tokens while preserving errors, file paths, line numbers, test names, user instructions, recent edits, and architecture decisions.