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 luanmorenommaciel/brief-spec --skill outcome-briefgit clone --depth 1 https://github.com/luanmorenommaciel/brief-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/skills/luanmorenommaciel/brief-spec/outcome-brief)<a href="https://agentmods.dev/skills/luanmorenommaciel/brief-spec/outcome-brief"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/brief-spec/outcome-brief/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/luanmorenommaciel/brief-spec/outcome-brief"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/brief-spec/outcome-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00069 | $0.00723 |
| Opus 5.5 | $0.00028 | $0.00289 |
| Sonnet 5.5 | $0.00014 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
outcome-brief 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 20d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- outcome-brief — 89% identical, 33 lines differ
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outcome Brief
End with one bounded brief that lets the reader recognize the outcome without rediscovering the response structure. Preserve uncertainty and source references; do not turn formatting into proof.
Workflow
- Determine the honest status:
DONE: requested outcome achieved and directly verified.REVIEW: implementation is ready for human inspection.DECIDE: a meaningful choice is required.BLOCKED: an external dependency prevents continuation.FAILED: the attempt did not achieve the requested outcome.
- State what is now true, not the activity performed.
- Identify the smallest human action. Use
Nonewhen no action is required. - Cite up to five inspectable proof references. Prefix each with its evidence basis and result:
[direct|derived|reported]/[pass|fail|info]. - State gaps without softening them.
- Give no more than three next actions and three open items.
- Render the fields exactly in the order below.
- If available, run
brief-spec validate outcome -before returning the brief.
Required output
<!-- briefspec:outcome:v1 -->
## Outcome Brief
Status: DONE
Outcome: One sentence describing what is now true.
Human action: None
Proof:
- [direct/info] `path/to/file:line` — what it proves
- [direct/pass] `command` → observed result
Gaps:
- None
Next:
- The next useful move, or None
Open:
- None
<!-- /briefspec -->
Keep None explicit; never omit a field in the full form. A DONE brief cannot contain required
human action or unresolved gaps, needs at least one [direct/pass] proof that you observed
yourself, and cannot include any fail proof; use REVIEW when the evidence is only derived or
reported. REVIEW, DECIDE, and BLOCKED require human action. BLOCKED and FAILED require a
gap and a next action. DECIDE requires an open decision; write it as a decision card:
Options: A; B — Recommendation: A — Reversible: yes — Needed by: <date>.
What ships with it
3 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.
- 20d ago Changed · +3 lines 131d57382d16
- 1mo ago Changed · +20 lines df1e1c6b00f1
- 1mo ago First seen · 62 lines · 69 tokens per session scan A 1078c25d1b2c
outcome-brief is a skill published in the GitHub repository luanmorenommaciel/brief-spec (30 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 723 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
hatch3r-cli-toolbox
Category-indexed reference for 34 specialist CLI tools beyond the always-on five (ripgrep, jq, gh, fd, fzf). Use to pick the right tool for HTTP clients, ai-chat, structural-search, sed-style edits, data ops, browser automation, container ops, and more.
hatch3r-handoff-prepare
Captures mid-work session state into a canonical handoff document at .hatch3r/handoffs/active/. Use when ending a session mid-work, switching tools, or after context-health Orange/Red.
hatch3r-cleanup
Repo-state cleanup pass — inventories accumulated hatch3r working state (plan files, workspace dirs, review telemetry, findings ledgers, learnings, handoffs, board staleness), asks once with per-category counts and estimated reclaim, dispatches each owned surface to its owning skill or CLI path, and prunes only the…
hatch3r-customize
Creates and manages customization files for any hatch3r artifact type (agents, commands, rules, skills). Supports model overrides, description changes, scope overrides, enable/disable control, and project-specific markdown instructions.
hatch3r-learn
Captures learnings from completed development sessions into reusable knowledge files for future consultation. Invoke manually, from board-pickup after PR merge, or with a specific issue number for targeted reflection.
hatch3r-cli-fd
User-friendly find replacement, gitignore-aware. Use when locating filenames or directories by glob with parallel walking; invoke fd. Outputs newline-separated hit records; bound results with -c or --max-count.