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 42-evey/hermes-plugins --skill work-ledgergit clone --depth 1 https://github.com/42-evey/hermes-pluginsWrote 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/42-evey/hermes-plugins/work-ledger)<a href="https://agentmods.dev/skills/42-evey/hermes-plugins/work-ledger"><img src="https://agentmods.dev/badge/skills/42-evey/hermes-plugins/work-ledger/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/42-evey/hermes-plugins/work-ledger"><img src="https://agentmods.dev/badge/skills/42-evey/hermes-plugins/work-ledger.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 | $0.00016 | $0.01073 |
| Opus 5.5 | $0.00006 | $0.00429 |
| Sonnet 5.5 | $0.00003 | $0.00215 |
| Haiku 4.5 | $0.00002 | $0.00107 |
Grade A, and why
work-ledger 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 today.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Ledger
Keep the state of long work in a markdown file on disk so it survives context compaction, /new, restarts and handoffs between agents. The todo tool lives in one session and /goal keeps one objective alive; the ledger holds every request, what is done and how it was tested, and where to resume.
When to Use
- Work spanning several sessions or days, or driven by
/loop,/goalor cron - A backlog of more than a few items, or a user who adds requests while you work
- Before a long autonomous run, or when the context is close to compaction
- Handing work to another agent, or picking it up from one
- Don't use for: a task that fits in one session;
todois enough
Location
- One ledger per project:
LEDGER.mdat the repo root, or outside the tree (for example~/.hermes/ledgers/<project>.md) when the repo must stay clean. - Save the path with
memoryso a new session finds it. - One agent owns the writes. Other agents report to the owner instead of editing the file.
Procedure
- Read the ledger once at the start of each cycle with
read_file. Act from the STOP line and the Doing/Todo lists. Do not rebuild state from code or old sessions; usesession_searchonly for something the ledger lacks. - Record every new user request before acting on it. Add it to Todo with the date and the user's words quoted verbatim. A reply to the current work is not a new request.
- Work one item at a time. Move it to Doing with the date and current state.
- Close only with a test note. Move it to Done with
tested:naming the exact check and its result (verify-before-done). No test note, no close. - Reopen what breaks. When a Done item turns out broken, move it back to Todo with
reopened: <date> <what failed>. Keep its ID; do not add a duplicate. - Record blockers and standing instructions. A blocked item names what it waits on: a user decision, hardware, another item ID. Durable user preferences go under Notes, verbatim.
- Log events. One line per commit, deploy or decision.
- End every session with a STOP line replacing the previous one: the item, the file, the next command, and any half-finished state (uncommitted changes, a running process and its PID file, a pending migration).
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.
- today First seen · 87 lines · 16 tokens per session scan A 124c1cffe5e3
work-ledger is a skill published in the GitHub repository 42-evey/hermes-plugins (534 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 1,073 once invoked, about $0.0001 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 2026-10-25.
Other skills, from other repositories
hermes-kanbanize
Use when an existing conversation, plan, specification, or objective must become a Hermes-native Kanban board with verifiable work slices, real blocking edges, a clear execution frontier, and no duplicate scheduler.
what-have-we-done-today
Use when a recap of today's sessions, cron, and kanban helps.
hermes-overnight-autonomy
Use for unattended Hermes continuity and watchdogs.
github-issues
Create, search, triage, and manage GitHub issues. Each section shows gh first, then the curl fallback.
flowai-live-dashboard-template
Team-management dashboard skill in the FlowAI aesthetic — three tabs (Team Members, Team Details, Activity Log), KPI stat row, member table, role distribution bar chart, online presence and activity sparklines, and a top-contributors panel, all in a single self-contained HTML file with light/dark theming, hoverable…
team-okrs
OKR tracker page — quarter banner, three objectives with their key results as progress bars, owner avatars, status pills, and a "this quarter at a glance" sidebar. Use when the brief mentions "OKRs", "key results", "objectives", or "目标".