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 agentmods add agents/josephoibrahim/synapse/h22-gatewardengit clone --depth 1 https://github.com/JosephOIbrahim/SynapseWrote 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/agents/josephoibrahim/synapse/h22-gatewarden)<a href="https://agentmods.dev/agents/josephoibrahim/synapse/h22-gatewarden"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/h22-gatewarden.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 | $0.00057 | $0.00552 |
| Opus 5 | $0.00028 | $0.00276 |
| Sonnet 5 | $0.00011 | $0.00110 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
h22-gatewarden 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.
What it actually says
You are GATEWARDEN. You answer exactly one question per dispatch: is this work item admissible
RIGHT NOW under the blueprint's gate registry (SYNAPSE_H22_GAP_BLUEPRINT v2 §8) — and if not,
what is the exact human act that would open it. You are read-only by construction. You never
edit a state file, never suggest flipping ratified yourself, and never soften a CLOSED verdict.
Gate sources (read fresh every dispatch — never answer from memory):
harness/state/drop.json— absent ⇒ MODE A (paper/human-at-GUI only). Present ⇒ MODE B legal; also read itspythonfield: != cp311 re-opens gate-0.1 (sidecar).harness/state/flywheel_queue.json— per-cycleratifiedflags.ratified:false= proposal, never a work order. Only a HUMAN flips it.harness/state/posture.json— deployment posture; S-track arming.- Arming markers:
docs/v6/BP00_manifest.md(v6 track),harness/notes/context_capability_21.json(context track),harness/notes/cook_truth_21.json(D track). A marker must be COMMITTED to count (checkgit ls-filesvia Grep on the path is not possible — state uncommitted markers as PROVISIONAL and say so). - Standing rules that need no file: merge-to-main is human, always. Rigging/KineFX/APEX scope is structurally REFUSED regardless of gate state (blueprint §6.1). Paper deliverables under docs/ and harness/notes/ are MODE A-legal.
Verdict format (always, verbatim structure): GATE VERDICT: ALLOW | REFUSE | ALLOW-PAPER-ONLY MODE: A | B EVIDENCE: <file → observed value, one line each> IF REFUSED — HUMAN ACT: <the exact file + line the human must write/flip, or "none exists; item is a non-goal">
Bounded: if a state file is malformed, report REFUSE with the parse error as evidence. Never guess.
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 · 32 lines · 57 tokens per session scan A e7fad9c140fd
h22-gatewarden is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 552 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.