Borrowing it
Nothing to install: this file belongs to the-sid-dani/second-brain-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/the-sid-dani/second-brain-os/main/.agents/skills/implement/SKILL.mdgit clone --depth 1 https://github.com/the-sid-dani/second-brain-osWrote 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/the-sid-dani/second-brain-os/implement)<a href="https://agentmods.dev/skills/the-sid-dani/second-brain-os/implement"><img src="https://agentmods.dev/badge/skills/the-sid-dani/second-brain-os/implement/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/the-sid-dani/second-brain-os/implement"><img src="https://agentmods.dev/badge/skills/the-sid-dani/second-brain-os/implement.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 | $0.00194 | $0.01269 |
| Opus 5.5 | $0.00078 | $0.00508 |
| Sonnet 5.5 | $0.00039 | $0.00254 |
| Haiku 4.5 | $0.00019 | $0.00127 |
Grade A, and why
implement 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 7d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement the work described by the user in the spec or tickets.
Resolve the project, its tracker and its paths from docs/agents/project-context.md. If a skill earlier in this conversation already resolved them, reuse that. When the work is written for people, load the rules of the Area the project belongs to (its parent_hq); they carry the voice and format rules. If the project has no Area (parent_hq: none or missing), use the voice in root SOUL.md and USER.md.
Asking for /implement on a ticket or spec is the go-ahead to build it inside its project and repo, commit on the ticket's branch, and update the tickets' status and delivery notes and the project's memory.md. It is not a go-ahead to push, merge, deploy, send, publish or change anything shared.
1. Read the work
- Find the ticket exactly. Resolve a ticket number through the project's tracker, never against whatever numbered list is in view. State its title back before starting. If the plan lives only in this conversation, say so and build from that.
- Read the whole ticket (description, acceptance criteria, comments; a triage agent brief is the contract), then the spec it hangs off for the audience, decisions and acceptance point.
- Blockers. If a blocker is still open, stop and say which one. A blocker that's closed but whose answer says the thing it was meant to produce hasn't arrived counts as open.
- Checkable criteria. If a criterion can't be checked as written, say which and propose a checkable version before building. Where the ticket and the spec disagree on form, the ticket wins; it's the narrower contract.
2. Route
Pick one path and read its reference before doing anything else:
| The request | Path |
|---|---|
| One ticket whose deliverable runs: an app, service, MCP server, script, hook, dashboard, site or prototype. A small written part (a README section, a changelog line) doesn't change that | references/code.md |
| One ticket whose deliverable is written for people: a doc, page, deck, diagram, plan, research write-up, video, email or Slack draft | references/knowledge-work.md |
| Every ticket in a spec at once ("the whole spec", "all the tickets", "land this spec") | references/whole-spec.md |
What ships with it
4 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.
- 7d ago First seen · 50 lines · 194 tokens per session scan A 0c1151d03388
implement is a skill published in the GitHub repository the-sid-dani/second-brain-os (3 stars, last pushed 7d ago), licensed MIT. It adds 194 tokens to every session and 1,269 once invoked, about $0.0008 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 2026-10-17.
Other skills, from other repositories
peer-onboard
A procedure for bringing an outside lead or peer into a shared working setup, including their contact space, records, previous conversations, and ongoing session.
contrib-watch
Watch incoming feedback from outside engineers on your open-source repos: comments, reviews, issues, mentions. Use when you need to find who replied to your pull requests or issues, triage human versus bot responses, and answer within a day with evidence.
retro-lost
Run a retrospective for an abandoned agent session (untouched for over 24 hours, never closed with a retro): rebuild context cold from the transcript, list what was built, sort Keep/Drop/Try and file the durable parts. Use from a nightly routine or on demand. Triggers: /retro-lost, retro for an abandoned session.
issue-match
Measure a target repository's queue and find a live open issue the contribution would close, before opening a pull request there. Reports how many PRs are open, how many of the last N closed ones were actually merged, and which issue to attach to, because a cold PR into a dead queue is a wasted artifact. Triggers…
local-engineer-outreach
An engineer-outreach workflow that manages ongoing conversations with engineering contacts and moves them through planned next steps toward an invitation or call to action.
outbound-gate
Gate for any outbound message before it leaves: pull request or issue comment, DM, invite, post, email. Use before sending to check facts, tone, platform rules, registry status and AI-slop, and to block text that fails.