Borrowing it
Nothing to install: this file belongs to 1cFE/fusion-tea. 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/1cFE/fusion-tea/main/.agents/skills/narrate-goal/SKILL.mdgit clone --depth 1 https://github.com/1cFE/fusion-teaWrote 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/1cfe/fusion-tea/narrate-goal)<a href="https://agentmods.dev/skills/1cfe/fusion-tea/narrate-goal"><img src="https://agentmods.dev/badge/skills/1cfe/fusion-tea/narrate-goal/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/1cfe/fusion-tea/narrate-goal"><img src="https://agentmods.dev/badge/skills/1cfe/fusion-tea/narrate-goal.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 | $0.00063 | $0.01626 |
| Opus 5.5 | $0.00025 | $0.00650 |
| Sonnet 5.5 | $0.00013 | $0.00325 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
narrate-goal 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 24d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before executing this skill, read .agentic-mbse/claude.md in Claude Code or .agentic-mbse/codex.md in Codex. Resolve supporting paths from this skill’s installed directory; keep generated outputs in the project or a temporary directory. Read referenced skills from .agents/skills/<name>/SKILL.md when their guidance is needed.
Narrate Goal
Create one human-readable account of what a goal's evidence supports at one cutoff. The narrative explains the starting problem, causal changes, measured results, limits, and useful visuals without becoming part of /run-goal.
Authority boundary
The narrative is derived presentation material. It is never evidence, state, authorization, a decision record, a review verdict, or an input cited by an authoritative artifact. If the narrative and a cited source disagree, the source wins.
Read from work/orchestration/goals/<goal-slug>/, but write only one new file under work/narratives/. Do not edit the goal, its evidence, native workflow records, earlier narratives, or project status files.
Intake and output
Get the canonical goal slug or goal-directory path from the request. Ask only if the target is missing or ambiguous. Confirm that goal.md, trail.md, and learnings.md exist.
Use the generation time in UTC and name the output work/narratives/YYYYMMDD-HHMMSSZ-<canonical-goal-slug>.md. Normal creation must not overwrite an existing file. If that exact path already exists, stop and report the collision.
Establish the source basis
- Record the base commit with
git rev-parse HEADand the UTC generation time. - Read
goal.md, thentrail.md, thenlearnings.md. Follow the authoritative native records they cite when those records are needed to support the story. - Determine goal-level closure from the authoritative trail. A closed round, an accepted learning, or a review that recommends closure does not close the goal. Treat the goal as closed only when the trail records the owner's close ruling; current goals use a
## Goal close — YYYY-MM-DDheading. Otherwise report it as open at this cutoff. - For a closed goal, take the calendar date and disposition from the close entry. If that entry has no explicit time, find the commit that first introduced its close heading and use the commit time only as a rough proxy. Label it
Git commit-time proxyand include the short commit id. If the entry is uncommitted or its introducing commit cannot be identified, state that the rough time is unavailable; never infer one from nearby work. - Do not use an earlier narrative,
CURRENT_WORK.md,SUMMARY.md, or other orientation prose as evidence. They may help locate a source, but every retained claim must resolve to a goal file or native record. - Check the goal files and every cited native record actually used with
git status --short -- <paths>immediately before writing. If relevant files changed while drafting, reread them before creating the snapshot. - Dirty sources are allowed. When any relevant input is dirty, label the cutoff
Provisional, record the base commit, state that uncommitted source content was included, and say that the exact source state may not be recoverable from Git.
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.
- 24d ago Changed · +5 lines 0220e8a886f7
- 1mo ago First seen · 80 lines · 63 tokens per session scan A 816f7ad74301
narrate-goal is a skill published in the GitHub repository 1cFE/fusion-tea (5 stars, last pushed 24d ago), licensed MIT. It adds 63 tokens to every session and 1,626 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 2026-09-29.
narrate-goal compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| narrate-goal1cFE/fusion-tea | Skill | 5 | 24d ago | MIT | A | 63 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |