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 commands/odinmb/ops-workflow/recapgit clone --depth 1 https://github.com/OdinMB/ops-workflowWhat 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 | $0.00105 | $0.01309 |
| Opus 5 | $0.00053 | $0.00655 |
| Sonnet 5 | $0.00021 | $0.00262 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
recap 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 2d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarize what happened in this project since the date specified: $ARGUMENTS
If no date is provided, ask the user for one.
Instructions
1. Parse the Date
Convert $ARGUMENTS to an absolute date (YYYY-MM-DD). Handle natural language like "last week", "March 1", "two weeks ago", "Monday". If the input is ambiguous or missing, ask the user.
Store the resolved date as $SINCE.
2. Gather Evidence
Collect changes from these sources. Read them in parallel where possible. Skip sources that don't exist.
a. Completed Plans
Read plans/completed/INDEX.md. Identify plans with date prefixes >= $SINCE. Read each matching plan file — focus on the Objective, Outcome, Key Decisions, and Artifacts sections.
b. Active Plans
Read plans/INDEX.md. Note any plans that were created after $SINCE (check their date prefix or file modification context). These represent work that started but hasn't finished yet.
c. Git History
Run git log --oneline --after=$SINCE to see commits in the date range. This captures changes that might not have corresponding plans (quick fixes, direct updates, autonomous work).
d. State File Changes
Grep all files under state/ for _Last updated: lines. Flag any with dates >= $SINCE — these represent reality that changed during the period.
e. New Artifacts
Scan artifacts/ (and subfolders) for files with date prefixes >= $SINCE. These are deliverables produced during the period.
f. MEMORY.md Changes
Check git log for commits that touched MEMORY.md since $SINCE. If any exist, note what Key Learnings or context was added.
g. Backlog Movement
Compare the current backlog state against git history to identify items that were added or removed since $SINCE. Use git log --oneline --after=$SINCE -- backlog/ to approximate this.
3. Assess Volume and Set Granularity
Count the total number of changes (completed plans + state updates + artifacts + significant commits). The output should scale with what actually happened — never pad quiet periods with filler. A busy period needs compression; a quiet period just needs less output.
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.
- 2d ago First seen · 136 lines · 105 tokens per session scan A 1937cb546497
recap is a command published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed 15d ago), licensed MIT. It adds 105 tokens to every session and 1,309 once invoked, about $0.0005 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 commands, from other repositories
standup
Dev standup — open Linear tickets grouped by in-flight, top priority, and backlog.
close-spec
Archive a completed OpenSpec change by name.
update-issue
Update an issue description with structured, evidence-backed content.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
camp-init
Initialize a new campaign workspace.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).