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 DheerG/swarms --skill reflect-outcomegit clone --depth 1 https://github.com/DheerG/swarmsWrote 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/dheerg/swarms/reflect-outcome)<a href="https://agentmods.dev/skills/dheerg/swarms/reflect-outcome"><img src="https://agentmods.dev/badge/skills/dheerg/swarms/reflect-outcome.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.01336 |
| Opus 5 | $0.00032 | $0.00668 |
| Sonnet 5 | $0.00013 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
reflect-outcome 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 8d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user stated an outcome in their own words. Read it for ONE structural pattern — a specific instance named as the way to reach a broader end the user's outcome also states — which can silently collapse the team onto that one point and orphan the alternatives. Fire ONLY when BOTH are present: (1) a named mechanism, product, or instance, AND (2) a wider goal stated anywhere in the user's outcome — not necessarily in the same sentence as the named instance — that the named thing is merely one way to serve. The named thing being narrower than that stated wider goal is the discriminator. Infer nothing: if no wider end is stated, do not fire (a category you could infer from the name is not a stated end), and never predict that foreclosure will happen — detect only the divergence the user's own words make plain. A bare concrete noun, mechanism or product, with no stated wider end does NOT fire; that over-firing is the alarm-fatigue failure this exists to avoid. The cheap, incumbent-first dismiss is what makes firing on a real signal safe.
- Mechanism-as-means: "force a resume so it can nudge a forgotten prospect" → "nudge" is one way to reach the wider stated goal "resurface a forgotten prospect" → FIRE. Contrast "add a retry queue for failed webhooks" → "retry queue" IS the whole ask, no wider goal it under-serves → stay SILENT.
- Proper-noun-specific-instance: "integrate with Salesforce so sales can see deals" → the wider end "sales can see deals" is stated and Salesforce is one way to reach it → FIRE. Contrast bare "store it in S3," "send a Slack notification," "cache it in Redis," "deploy on Vercel" → the product IS the ask, no wider end stated → stay SILENT. Do NOT fire on the class you could infer from the product name — that inference is the alarm-fatigue over-fire; an existing-integration collision with no stated end drops to the Research-phase repo check instead.
Scan the whole input, not a single clause: if more than one pin is present, fork on the single most consequential one; if it is genuinely ambiguous which matters most, return NO FORK.
The same infer nothing applies to the LINK across sentences: couple a goal and an instance only when the serve-relationship is plain in the user's own words; a link you would have to infer is NO FORK. When the outcome names more than one instance, pair each only with the end it plainly serves — never fire an instance against an end that belongs to a different named thing.
Read the WORDING only. Do not read the codebase. Do not grade quality. Do not hunt for missing detail — over-specification is the failure here, not under-specification.
Common case — nothing pinned: return exactly NO FORK. The lead shows the user nothing and carries the outcome forward as-is. Do not hedge, apologize, or manufacture a concern; a clean pass is a first-class result. Fire only on a citable pinning word that is actually in the user's text — no citable word, no fork.
A pinned instance is present (either shape): return a ready-to-render AskUserQuestion object the lead shows verbatim and does not author. Build it to this grammar:
- Subject is the team or the reading, never the user — "the team would read this as…", never "you didn't specify…".
- Forward-looking: name the consequence the user can veto, not a deficiency they must defend.
- Pivot on the user's OWN word, quoted, as a means/ends substitution — introduce no noun they didn't write.
- Only remedy is to pick a reading — never to add more detail.
Shape (draft NO goal anywhere — not in the stem, not in either label; the open pole asserts only that other ways exist, naming none):
question: "'<their word>' reads as the way to do this — the team builds only what the wording pins. Did you mean <their word> specifically, or are you open to other ways to do this?"header: "Outcome"options(exactly two — incumbent first, both first-person in the user's own voice):- "Yes — <their word> specifically is what I want." — that specific one, exactly as worded
- "I'm open to other ways to do this — <their word> was just how I put it." — <their word> was one example, not the requirement
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.
- 8d ago First seen · 40 lines · 65 tokens per session scan A bb69ccf34e4a
reflect-outcome is a skill published in the GitHub repository DheerG/swarms (85 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,336 once invoked, about $0.0003 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 skills, from other repositories
pocket-development
Use when executing implementation plans of one or more tasks. Trigger on execute plan, delegate tasks, dispatch subagents. Combines delegate handoff discipline with prompt-engineering attention mechanics.
pocket-planning
Converts a pocket-grinding spec into a TDD-structured execution plan of full Pocket Packets. Use when pocket-grinding handoff arrives (spec path + acceptance criteria). Trigger on "create plan", "build plan", "pocket-planning", or when pocket-grinding skill invokes this. Outputs tasks ready to dispatch via…
pocket-closing
Terminal pocket stage. User invokes after pocket-development's phase-level pass writes verdicts. Reconciles reviews against log.json, gates on REVIEWFAIL/REVIEWBLOCKED, advances REVIEW→DONE, runs log close, and emits a closeout summary. Trigger on "pocket-closing", "close the plan", "close out", "finalize plan", or…
pocket-grinding
BDD-driven feature/fix discovery before any implementation. Use when planning a feature, designing a fix, or exploring options before building. Trigger on "pocket-grinding", "brainstorm", "think through", "plan this", "before we build". Invokes pocket-planning at handoff.
pocket-help
Onboarding and routing guide for the Pocket skill ecosystem. Use when someone asks what Pocket is, which Pocket skill to use, how the end-to-end flow works, or when Pocket is better than lighter Superpowers-style flows. Trigger on "what is pocket", "how do I use pocket", "which pocket skill", "explain pocket"…
pocket-pitching
Pre-grinding problem exploration. Use BEFORE pocket-grinding when the problem is unformed or needs exploration. Guides diverge→converge with structured brainstorming methods and LLM-to-LLM curation (advisor tool), then produces a pitch exploration doc. Trigger on "pocket-pitching", "pitch this", "explore this idea"…