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 IgorGanapolsky/ThumbGate --skill gsd-ralph-context-loopgit clone --depth 1 https://github.com/IgorGanapolsky/ThumbGateWrote 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/igorganapolsky/thumbgate/gsd-ralph-context-loop)<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/gsd-ralph-context-loop"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/gsd-ralph-context-loop/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/igorganapolsky/thumbgate/gsd-ralph-context-loop"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/gsd-ralph-context-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00099 | $0.00646 |
| Opus 5 | $0.00049 | $0.00323 |
| Sonnet 5 | $0.00020 | $0.00129 |
| Haiku 4.5 | $0.00010 | $0.00065 |
Grade A, and why
gsd-ralph-context-loop 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 10d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GSD + Ralph Loop for ThumbGate coding
GSD (Get Shit Done)
| Stage | Agent does | Artifact |
|---|---|---|
| Capture | List failures / goals / evidence gaps | Notes or issue bullets |
| Clarify | Skill vs MCP vs hook vs subagent | Layer decision |
| Organize | Files, PR branch, Linear claim, vault | Ledger |
| Execute | Implement + tests (parallel when independent) | Diff + green tests |
| Review | Probes, adversarial verify, three-bus ship | TRUE/FALSE ledger |
Never jump to Execute without Clarify (wrong layer = inert gates / thrash).
Ralph Loop (always-on improvement)
| Stage | Surface |
|---|---|
| Observe | Session preflight, gate-stats, CI, vault |
| Act | Tools under PreToolUse walls |
| Feedback | Thumbs / incident / capture_feedback |
| Promote | Matchable force-gate / auto-promote |
| Enforce | gate-check + deterministic guards |
Ralph without Promote→Enforce is analytics only.
Promote without matchable surface is AGENT-259 theater.
Parallel agents (when)
| Use parallel / workflow | Stay serial |
|---|---|
| PR multi-lane review | One-line fix |
| Enforcement audit | Single file |
| Skills + docs + tests independent | Shared-file conflict |
| Linear top-10 triage | Already claimed by sibling |
Default workflows:
/pr-adversarial-review/thumbgate-enforcement-audit/context-engineering-pr-check/linear-top10-triage
Session execute recipe
# Observe
bash ~/.grok/skills/multi-agent-coord/scripts/session_preflight.sh
bash ~/.grok/skills/three-bus-ship-cycle/scripts/ship_cycle_status.sh
# GSD Capture/Clarify via checklist skill
# Execute with worktree branch
# Review
bash ~/.grok/skills/three-bus-ship-cycle/scripts/ship_cycle_check.sh <PR> <AGENT-ID>
Completion gate
Before done/shipped/fixed:
- Review probes green
- Three-bus updated
- No prose-only gates
- No stolen Linear locks
Related
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.
- 10d ago First seen · 82 lines · 99 tokens per session scan A 77a086355764
gsd-ralph-context-loop is a skill published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 646 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 2026-08-30.
Other skills, from other repositories
agentguard
Runtime guardrails for AI coding agents. Stop loops, budget overruns, retry storms, and timeouts before they burn money. Zero dependencies, local-first, MIT licensed.
crm-pipeline-playbook
How to answer pipeline, renewal, and account-health questions using the CRM tools.
deciding-who-decides
Decides who holds authority for a change — the agent at the edge or a human gate — by matching decision rights to reversibility, evidence, and consequence, and names the escalation trigger. Use when an agent could act on something irreversible, trust-bearing, or thinly evidenced. Do not use for trivial reversible…
staying-on-mission
Tests the current work against a written, lasting mission anchor and forces one choice, re-anchor, escalate, or stop. Use when an agent keeps finishing tasks but the work drifts from the goal, scope creeps, the same action repeats in a loop, or standards slip one small step at a time. Do not use for a tiny edit with…
verifying-final-artifacts
Verifies the delivered artifact a consumer actually receives (a figure, chart, PDF, SVG, screenshot, compiled build, or deployed response) by regenerating it fresh and directly observing the output, not the source that produces it, and ends in one honest verdict. Use when the deliverable is a produced artifact and…
closing-stale-packets
Brings an abandoned or half-filled change packet to an honest terminal state by completing it, closing it with a recorded rationale, or deleting it. Use when ng status flags a scaffold or invalid packet, a long session left a draft behind, or work was abandoned mid-packet. Do not use for an actively in-progress…