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 asimons81/hermes-field-kit --skill what-have-we-done-todaygit clone --depth 1 https://github.com/asimons81/hermes-field-kitWrote 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/asimons81/hermes-field-kit/what-have-we-done-today)<a href="https://agentmods.dev/skills/asimons81/hermes-field-kit/what-have-we-done-today"><img src="https://agentmods.dev/badge/skills/asimons81/hermes-field-kit/what-have-we-done-today/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/asimons81/hermes-field-kit/what-have-we-done-today"><img src="https://agentmods.dev/badge/skills/asimons81/hermes-field-kit/what-have-we-done-today.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 26 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00023 | $0.01372 |
| Opus 5 | $0.00012 | $0.00686 |
| Sonnet 5 | $0.00005 | $0.00274 |
| Haiku 4.5 | $0.00002 | $0.00137 |
Grade A, and why
what-have-we-done-today 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 12d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What Have We Done Today
Overview
A manual, on-demand daily recap for any Hermes installation. It scans three local surfaces for today's activity — sessions (default profile plus every named profile, all sources), kanban boards (done today, running, blocked, todo/ready), and cron stores (jobs that ran, errored, are running now, or are due today) — then writes a plain append-friendly daily markdown log the user can read to remember what happened and what is still open.
Stdlib Python only. Read-only on all databases (mode=ro); the only write is
the daily markdown file in the recap directory. It is intentionally NOT a
cron job: it runs when a human actually wants the recap (tired, stoned,
context-switch heavy, or closing out the day).
When to Use
- "What have we done today?" / "Recap today" / "What did I get up to today?"
- The user lost track of a busy multi-project day and wants the threads pulled together.
- Before shutting down for the night: capture progress + leftovers.
Counter-triggers — do NOT load this skill when:
- The user asks about a specific past session or topic (use session search).
- The user wants a recurring scheduled recap (this skill is manual-only).
- The user wants to mutate sessions, kanban cards, or cron jobs.
Workflow
- Scan all three surfaces. Invoke through the
terminaltool:python3 ~/.hermes/skills/productivity/what-have-we-done-today/scripts/today_sessions.py --excerptsOutput: sessions grouped by profile (time, source, title, counts, goal/outcome hints), then kanban per board (done today, ▶ running, ✋ blocked, todo/ready counts), then cron (ran today with ❌ on errors, ▶ running now, ⏳ due today after an error). - Separate the signals. User-facing session sources are
desktop,cli,telegram.kanbansessions are worker lanes (generic titles — outcome comes from the excerpt, not the title). Cron ❌/⏳ rows are real breakage candidates;runningexecutions are work happening right now. - Drill where it matters.
session_searchreads only the current profile's DB; use it for ambiguous or high-stakes default-profile sessions. For sessions fromprofiles/*/state.db, the scanner's excerpts are the cheap evidence. - Split Done vs Open. Done = a verified outcome (session excerpt,
kanban done-today card, cron
okrun). Open = kanban ▶/✋/todo cards, cron ❌/⏳ rows, sessions with no resolution. Never infer completion from a session merely existing. - Pull open items (optional).
--ledger FILElists non-completed items from a task ledger JSON:{"items": [{"id", "title", "status", "next_action", "updated_at"}]}. Statuses other thancompleted/cancelledcount as open. - Write the log. Target
$RECAP_DIR/YYYY-MM-DD.md(default~/.hermes/daily-recaps/); create the directory if missing. Create the file with a# YYYY-MM-DDheading if absent; otherwise append a## Daily recap — HH:MMsection with Done / In flight / Needs attention bullets. Re-runs the same day append new sections. - Brief the user. Compact and ranked: ✅ Done today, 🟡 Still open, ⛔
Needs you, Next pick. Include
@session:default/<id>links for anything they might reopen.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 109 lines · 23 tokens per session scan A eca6ca9a6b3d
what-have-we-done-today is a skill published in the GitHub repository asimons81/hermes-field-kit (125 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,372 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 2026-08-30.
Other skills, from other repositories
slack-tools
Slack workspace management and automation specialist.
write-workflow-as-code
MUST use when writing or modifying Windmill Workflow-as-Code scripts using workflow, task, step, sleep, approvals, taskScript, taskFlow, taskscript, or taskflow.
memory-tasks
Task management via Basic Memory schemas: create, track, and resume structured tasks that survive context compaction. Uses BM's schema system for uniform notes queryable through the knowledge graph.
kill-the-standup
Reads yesterday's Linear issues and GitHub commits for the authenticated user, formats a standup update (done / doing / blockers), and posts it to Slack. Use when asked to write a standup, generate a standup update, post to the standup channel, summarize yesterday's work, or automate the daily standup. Trigger when a…
pir-action-tracker
Parses Post-Incident Review (PIR) pages in a Confluence space, fetches live status from referenced Jira tickets, updates action item tables with current status and due dates, marks completed PIRs with a visual closure panel, and surfaces any overdue actions for follow-up. Designed for Customer Success, Support, and…
perseus
Use when you need a bounded, local Perseus context render before an assistant reads project state. Perseus resolves selected workspace inputs such as git, services, sessions, and task notes into markdown. Use for deterministic session starts, workspace audits, and explicit context handoffs.