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.
git clone --depth 1 https://github.com/mohammad19974/bounded-relayWrote 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/commands/mohammad19974/bounded-relay/speckit.boundedrelay.handoff)<a href="https://agentmods.dev/commands/mohammad19974/bounded-relay/speckit.boundedrelay.handoff"><img src="https://agentmods.dev/badge/commands/mohammad19974/bounded-relay/speckit.boundedrelay.handoff.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 | $0.00008 | $0.00309 |
| Opus 5 | $0.00004 | $0.00154 |
| Sonnet 5 | $0.00002 | $0.00062 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
speckit.boundedrelay.handoff 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.
What it actually says
Refresh the Consumer Handoff
After all review and convergence gates pass, write the proposed handoff only to
the run-local handoff-draft.md named by evidence/handoff-context.json. Do
not edit .specify/agents/HANDOFF.md directly. The following verifier
revalidates the complete proof chain and atomically publishes the draft to that
canonical path only after every binding check passes.
Record objective, scope, active artifacts, frozen revision, routing target and actual effort split, Claude-host and Codex task ownership, accepted patches, changed files, checks and outcomes, review evidence paths, blockers, next exact action, and rollback notes. Distinguish estimated effort from observed Codex usage; do not invent Claude token use, cost savings, percentages complete, or model identity. Never store prompts, raw output, credentials, private payloads, or chain-of-thought.
Read the run-local evidence/handoff-context.json named in $ARGUMENTS and
place its exact marker once, unchanged, on the standalone final line of the
draft. Replace any older boundedrelay-handoff-v1 marker in that draft. The
following verifier rejects a missing, duplicated, stale, or manually
reconstructed proof binding.
This command does not commit, push, publish, deploy, or modify an external system.
$ARGUMENTS
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 · 33 lines · 8 tokens per session scan A 90dbedd80ec7
speckit.boundedrelay.handoff is a command published in the GitHub repository mohammad19974/bounded-relay (1 stars, last pushed 6d ago), licensed MIT. It adds 8 tokens to every session and 309 once invoked, about $0.0000 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 commands, from other repositories
tokendiet
Audit your code for wasteful LLM API spend and get a concrete plan to cut it — cache, batching, retry caps, prompt bloat. No fabricated numbers.
config-edit
Edit llm-redact config with the dashboard editor's guardrails: change rules, modes, deny strings, allowlists, NER, providers; validate; hot-reload.
status
Show llm-redact proxy status: counters, detections by type, and the protection posture.
users
List llm-redact named users and seats; guide invites and revokes.
audit
Verify the llm-redact tamper-evident audit chain.
config-show
Show the effective llm-redact configuration (env overrides named).