Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sgaabdu4/building-flutter-appsnpx agentmods add skills/sgaabdu4/building-flutter-apps/heWrote 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/sgaabdu4/building-flutter-apps/he)<a href="https://agentmods.dev/skills/sgaabdu4/building-flutter-apps/he"><img src="https://agentmods.dev/badge/skills/sgaabdu4/building-flutter-apps/he/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/sgaabdu4/building-flutter-apps/he"><img src="https://agentmods.dev/badge/skills/sgaabdu4/building-flutter-apps/he.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 | $0.00027 | $0.00349 |
| Opus 5.5 | $0.00011 | $0.00140 |
| Sonnet 5.5 | $0.00005 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
he 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 21d 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
Hard Eng
Select the matching route automatically from the task and current stage; no explicit skill invocation is required. Load only matching routes and continue to the next authorized stage when its prerequisites pass.
flowchart LR
T{Task} -->|Plan new work / changed scope| P[../he-plan/SKILL.md]
T -->|Implement / fix / resume build| B[../he-build/SKILL.md]
T -->|Ship / PR / merge / deploy| S[../he-ship/SKILL.md]
T -->|Repeated failures / lasting decisions| L[../he-learn/SKILL.md]
T -->|Task context / review| W[references/workflow.md]
T -->|Adapt / repair checks| G[references/gates.md]
T -->|Bulk / async / performance| E[references/efficiency.md]
T -->|Design / change / review tests| Q[references/testing.md]
T -->|Setup / update / MCP failure| I[references/integrations.md]
click W "references/workflow.md"
click P "../he-plan/SKILL.md"
click B "../he-build/SKILL.md"
click S "../he-ship/SKILL.md"
click L "../he-learn/SKILL.md"
click G "references/gates.md"
click E "references/efficiency.md"
click Q "references/testing.md"
click I "references/integrations.md"
What ships with it
15 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.
- references/efficiency.md 3.2 KB
- references/gates.md 37 KB
- references/integrations.md 6.3 KB
- references/requirements.md 3.9 KB
- references/testing.md 7.1 KB
- references/workflow.md 4.3 KB
- security/dart.yaml 896 B
- security/swift.yaml 3.9 KB
- semgrep/python.yaml 571 B
- templates/DESIGN.md 1.2 KB
- templates/hard-eng.dart.json 3.7 KB
- templates/hard-eng.javascript.json 4.4 KB
- templates/hard-eng.python.json 5.5 KB
- templates/hard-eng.swift.json 3.2 KB
- templates/PRODUCT.md 789 B
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.
- 21d ago Changed · +2 lines 1703297d31d2
- 28d ago First seen · 29 lines · 27 tokens per session scan A 29cf6565e606
he is a skill published in the GitHub repository sgaabdu4/building-flutter-apps (25 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 349 once invoked, about $0.0001 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.
Other skills, from other repositories
speckit-gh-triage-triage
Fetch open GitHub issues, classify each as bug, feature, or chore, then DELEGATE to the correct extension: bugs → bug.fetch (saved under .specify/bugs/), chores → chore.fetch (saved under .specify/chores/), features → speckit.specify (saved under specs/). Never save bugs or chores as specs.
speckit-chore-fetch
Load an existing GitHub issue into the chore workflow and seed a triage draft.
speckit-bug-issue
File a GitHub issue from a bug assessment (the 'report' phase) and record the issue link.
speckit-chore-issue
File a GitHub issue from a chore assessment (the 'report' phase) and record the issue link.
speckit-spec-stats-report
Main generator — scans all specs//, derives per-feature stage, task progress, health, last updated; when the TDD extension is installed, adds a deep TDD table (acceptance/unit/characterization counts, DONE, loop mode, tasks.md state); renders dashboard to configurable output path and writes .specify/stats/stats.json…
speckit-spec-stats-open
On-demand view of everything not complete: what stage each is stuck at, what the immediate next artifact/command is, oldest-untouched first, stale warnings past staleafterdays.