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/Mininglamp-OSS/octo-specWrote 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/commands/mininglamp-oss/octo-spec/octospec-finish)<a href="https://agentmods.dev/commands/mininglamp-oss/octo-spec/octospec-finish"><img src="https://agentmods.dev/badge/commands/mininglamp-oss/octo-spec/octospec-finish/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/commands/mininglamp-oss/octo-spec/octospec-finish"><img src="https://agentmods.dev/badge/commands/mininglamp-oss/octo-spec/octospec-finish.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 | $0.00017 | $0.00675 |
| Opus 5 | $0.00009 | $0.00338 |
| Sonnet 5 | $0.00003 | $0.00135 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
octospec-finish 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.
What it actually says
You are running the octospec Finish phase for task $ARGUMENTS.
- Run the final verification gate one more time (lint / type-check / tests).
- Write
.octospec/journal/shared/$ARGUMENTS.md— a short, team-visible record: what was done, any structural learning, any gotcha worth remembering. Start the file with OKF frontmatter (type: Journal, plustitle/description/tags/timestamp) so it stays a valid OKF unit and passesoctospec-lint. Also add a dated entry to.octospec/log.md(create it if missing). - Learning promotion (in-place write-back, same PR). If this task produced a
reusable learning, land it in this same PR — do NOT stage it in
learnings/pending/for a separate PR or a later move (that PR never happens, so the learning stays stranded on the feature branch). Two cases:- Existing rule applies → edit the relevant
.octospec/rules/<rule>.mdin place (add/refine a bullet), bump itstimestamp, and note the change in the journal. The PR review IS the gate for the rule edit. - No rule fits yet → create a new
.octospec/rules/<slug>.mdwith full OKF frontmatter (type: Rule,title,description,inject_when,priority,load_bearing,tier,source,timestamp) and add it torules/_index.yaml. The helper.octospec/scripts/octospec-update-spec.shgives you the raw material for this —--kind=rulewrites a rule draft tolearnings/pending/<slug>-rule-draft.mdplus a promotion block (proposed body + COMPREHENSION questions) on stdout;--kind=taskwrites a per-actor journal entry. The helper never auto-writesrules/(that keeps the comprehension gate human), so you copy the draft intorules/<id>.mdand update_index.yamlhere, in this PR — then drop the scratch draft. The draft is in-PR scratch, not a deliverable to promote later. Only leave something inlearnings/pending/when the learning is genuinely unresolved (needs human design before it can become a rule) — pending is for open questions, not for finished learnings awaiting a phantom review PR.
- Existing rule applies → edit the relevant
- Open a PR. Pre-fill the body using
.github/PULL_REQUEST_TEMPLATE.md:- Linked Spec →
.octospec/tasks/$ARGUMENTS/brief.md - COMPREHENSION three questions answered to substance (for load-bearing / architectural / P0 changes; omit for trivial ones).
- Linked Spec →
- Commit with a Conventional Commit message referencing the issue.
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 · 40 lines · 17 tokens per session scan A 88f81436dc43
octospec-finish is a command published in the GitHub repository Mininglamp-OSS/octo-spec (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 675 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.