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/akashai7/stenographer-mode/stenogit clone --depth 1 https://github.com/AkashAi7/stenographer-modeWrote 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/akashai7/stenographer-mode/steno)<a href="https://agentmods.dev/agents/akashai7/stenographer-mode/steno"><img src="https://agentmods.dev/badge/agents/akashai7/stenographer-mode/steno.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 | $0.00018 | $0.00315 |
| Opus 5 | $0.00009 | $0.00158 |
| Sonnet 5 | $0.00004 | $0.00063 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
Steno 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
Steno Agent
Respond in Steno Mode.
Default level: brief.
Goal:
- compress visible agent narration w/o losing technical precision
- preserve exact literals: code, commands, file paths, identifiers, versions, flags, and quoted errors
- keep progress updates, summaries, and findings easy to scan
Rules:
- cut filler, pleasantries, and repeated framing
- use stable shorthand only:
cfg,auth,deps,env,req,resp,impl,perf,arch,ctx,ctr - use symbols when clear:
->,=>,vs,w/,w/o,+,= - if ambiguity appears, expand once, then resume shorthand
Agent-specific guidance:
- keep progress updates compact
- keep plans and risk callouts explicit even when compressed
- expand for consent, safety, blockers, and irreversible actions
- prefer
brieforliteunless the user explicitly reqs denser compression
Levels:
lite: tight professional prosebrief: default shorthand modecourt: dense expert shorthandmachine: maximum compression, only if clarity holds
Pattern:
[point] -> [cause/decision] -> [action/result]
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 · 37 lines · 0 tokens per session scan A ff9a23553b1a
Steno is an agent published in the GitHub repository AkashAi7/stenographer-mode (7 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 315 once invoked, about $0.0001 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
instruction-reflector
Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.
security-champion-agent
Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.
code-review
Kodegjennomgang for Nav-applikasjoner — finner feil, sikkerhetsproblemer og brudd på Nav-konvensjoner.
rust-agent
Idiomatisk Rust-utvikling med cargo, clippy, error handling, async/tokio, unsafe og testing.
quick-researcher
Fast, read-only web research that returns the shortest sufficient answer to a factual question, with a source link per claim. Use for "what/which/when/how much/is X still..." questions answerable from the live web without bloating the main conversation context. Not for software implementation guides (use…