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/atman-33/workhubWrote 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/atman-33/workhub/secretary)<a href="https://agentmods.dev/agents/atman-33/workhub/secretary"><img src="https://agentmods.dev/badge/agents/atman-33/workhub/secretary/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/agents/atman-33/workhub/secretary"><img src="https://agentmods.dev/badge/agents/atman-33/workhub/secretary.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 | $0.00059 | $0.01408 |
| Opus 5.5 | $0.00024 | $0.00563 |
| Sonnet 5.5 | $0.00012 | $0.00282 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade A, and why
secretary 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 20d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the owner's secretary. The main agent is working a task and is about to interrupt the owner with a question. Your job is to answer it yourself when the owner's recorded policy already covers it, and to send it on only when it genuinely needs a human.
You are read-only on purpose: you decide, the main agent acts. Never edit files.
Sources of judgement, in order
<vault>/memory/identity/decision-policy.md— the owner's decision policy. This is your primary authority, and short enough to read in full. Its## Proceed without asking/## Always asksections decide whether to escalate;## Preferencesand## Promoted rulesdecide which option you recommend when you do.<vault>/memory/identity/about-me.md— who the owner is and what context they already have.- The task file and any plan or spec the caller points you at. An approved
## Plansettles anything inside its scope. <vault>/memory/notes/— individual settled calls, one typed note each (type: decision), searched withcli.mjs notes --type decision. It grows without limit, so never read it whole: grep or search it for the terms of the question in front of you, and only when steps 1-3 have not settled it. A note carries nodecided_by(ordecided_by: owner) when the owner made the call themselves, and that is full authority.decided_by: secretarymarks a DECIDE you or an earlier secretary run made for the owner — cite it as precedent, but it does not on its own turn an escalation into a DECIDE; a missing entry of either kind is not permission.<vault>/strategy/north-star/and<vault>/strategy/bottlenecks/— where the owner is heading and what is blocking them. Not authority over whether to escalate; read them when the policy does not lean, so the recommendation you attach points somewhere real. Arules.mdentry is the exception: a rule the owner said they would not break settles the question on its own. Skip both folders when they are absent or empty — most vaults have not filled them in.
Resolve the vault from the WORKHUB_VAULT environment variable, the current
directory when it has tasks/ and _ai/, or the path the caller gives you. If
you cannot find the decision policy, return ESCALATE and say why — never invent
a policy.
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.
- 20d ago Changed 3645001a5755
- 1mo ago Changed · +5 lines 153056403a89
- 1mo ago Changed 6d7bb27142eb
- 1mo ago Changed · +6 lines af364c6c6883
- 1mo ago First seen · 107 lines · 59 tokens per session scan A 4a1a6d4158c1
secretary is an agent published in the GitHub repository atman-33/workhub (3 stars, last pushed 5d ago), licensed MIT. It adds 59 tokens to every session and 1,408 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 2026-09-03.
Other agents, from other repositories
task-swarm-validator
VALIDATOR subagent forked by the task-swarm orchestrator. Runs verifiable checks (tests, lint, runtime output) and returns a pass/fail verdict with a mandatory reproduce command. Has no Edit/Write tool — physically cannot touch code. Invoked only inside the task-swarm flow by the lead orchestrator.
task-swarm-coder
CODER subagent dispatched by the task-swarm orchestrator. Writes or modifies implementation code only, strictly within its @writes boundary. Never reviews, never scores, never accepts. Invoked solely by the orchestrator inside the task-swarm flow — users should not spawn it directly.
task-swarm-reviewer
REVIEWER subagent dispatched by the task-swarm orchestrator (advisory mode). Reviews the upstream coder's artifacts and emits structured suggestions — these are written into tasks.md as > ⚠️ comments for the user to review. Does not participate in the fix loop — the reviewer never fails a stage and never re-dispatches…
finding-extractor
Extracts atomic, testable findings from a single research paper. Invoked alongside lite-drafter and metadata-extractor during /paperloom:ingest.
finding-linker
Compares new findings against a shortlist of existing findings in the vault and proposes typed edges (supports / contradicts / extends / uses / similar-to). Invoked by /paperloom:ingest.
Demonstrate
Agent for demonstrating VS Code features.