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 OdinMB/ops-workflow --skill updategit clone --depth 1 https://github.com/OdinMB/ops-workflowWrote 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/odinmb/ops-workflow/update)<a href="https://agentmods.dev/skills/odinmb/ops-workflow/update"><img src="https://agentmods.dev/badge/skills/odinmb/ops-workflow/update/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/odinmb/ops-workflow/update"><img src="https://agentmods.dev/badge/skills/odinmb/ops-workflow/update.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 | $0.00037 | $0.01637 |
| Opus 5.5 | $0.00015 | $0.00655 |
| Sonnet 5.5 | $0.00007 | $0.00327 |
| Haiku 4.5 | $0.00004 | $0.00164 |
Grade A, and why
update 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update
Ingest external information into this ops repo's knowledge base. Two modes depending on whether arguments are provided.
Detect Mode
- If
$ARGUMENTSis non-empty → Inline mode: the arguments contain the information to integrate. - If
$ARGUMENTSis empty or blank → Inbox mode: process files from.update/.
Inline Mode
The user provided content directly: $ARGUMENTS
-
Load context. Read
CLAUDE.md,MEMORY.mdandcharter.mdto understand the repo structure, goals, and current state. -
Classify the information. Apply the whole-file test from CLAUDE.md — fact about the world, or decision/framework?
- Fact about the world (status, metric, inventory) →
state/ - Decision / strategy / framework / guardrails / research →
references/ - Specific actions to do next →
backlog/ - Delivered output →
artifacts/ - Strategic insight → may also warrant a MEMORY.md Key Learnings update
- Mixed → split
Trap: "current strategic posture" content feels state-shaped but is forward-looking strategy →
references/.A changed goal, audience or non-goal goes into
charter.md, and only when the user says that is what changed; when a source merely suggests it, ask (step 3). Where the repo's CLAUDE.md has an## Autopilotsection, a product or feature idea goes intobacklog/ideas.md, for autopilot to route to a repository, andstate/autopilot.mdandreferences/autopilot-policy.mdare never edited: they are autopilot's own. There, too, user feedback (anything in a user's own voice: a reply, a review, a complaint, a request) goes only intoreferences/users/feedback.md, newest first, one line each:- YYYY-MM-DD · <source type> · <persona, if one fits> — <the substance>. Anonymise it before writing: remove names, email addresses, handles, phone numbers, street addresses, account IDs and anything else that identifies a person; make a place finer than a city the city; keep the substance, the date and the kind of source; never store a screenshot of someone's message. Feedback goes nowhere else in the repo. - Fact about the world (status, metric, inventory) →
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 Changed · +1 lines a4b67135c487
- yesterday Changed · +2 lines 9b47681e5b28
- 1mo ago First seen · 89 lines · 37 tokens per session scan A 8c2b329fe464
update is a skill published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,637 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 2026-08-31.
Other skills, from other repositories
domain-extract
Extract domain knowledge from existing project sources and generate domain rules. Also handles vault sync and domain listing.
capture-practice
Captures an insight or practice discovered during work and registers it in the dotforge practices/inbox.
harden-memories
Audit the bd remember store and recommend which entries to prune, so each one earns its per-session bd prime injection cost. Read-only: it proposes a triage table plus the exact bd forget / migration commands; you run them. Use when bd remember entries have accumulated, feel stale, redundant, or conflicting, or when…
handoff
Workflow for compacting the current conversation into a handoff document that another Claude Code session can pick up from later. Produces a single Markdown file capturing the goal, current state, in-flight work, decisions made, open questions, paths touched, and a recommended next-session skill — referencing existing…
megg-state
Hand off an unfinished session to the next one — what's done, what's next, what's blocked.
knowledge-maintain
This skill should be used when the user asks to fix, repair, or tidy one or more SPECIFIC named notes — 'fix these notes', 'fix the issues in [note]', 'add the missing relations to [note]', 'tidy up [note]', 'fix orphan [note]', 'apply the gardener findings for [note]'. Applies structural fixes (missing sections…