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 agentmods add skills/devantler-tech/agent-plugins/needs-stack-mappingnpx skills add devantler-tech/agent-plugins --skill needs-stack-mappinggit clone --depth 1 https://github.com/devantler-tech/agent-pluginsWhat 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 | $0.00109 | $0.00952 |
| Opus 5 | $0.00055 | $0.00476 |
| Sonnet 5 | $0.00022 | $0.00190 |
| Haiku 4.5 | $0.00011 | $0.00095 |
Grade A, and why
needs-stack-mapping 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 yesterday.
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Needs → stack mapping
The person you are assisting describes what they want in the vocabulary of their product — an
outcome ("people should be able to book a session"), an audience ("my newsletter readers"), a
workflow ("when someone pays, send them the files"). Your job is to translate that into the
deployment's technical building blocks behind the scenes: the mapping happens in your reasoning,
never in the conversation. Conducted in the register of the jargon-free-voice skill.
Where the building blocks come from
The allowed building blocks are deployment-owned configuration, not part of this skill: the
consuming deployment's canonical instructions file (AGENTS.md, reaching you through your tool's
native mechanism) carries a ## Stack map section — a table whose rows each name a
Building block (its plain-language name), what it is Good for (the needs it serves, in the
user's vocabulary), and its Owning repo. That table is your entire menu:
- Match needs against the Good for column. It is written as a matching surface — compare the user's stated outcome/audience/workflow against each row's purposes semantically, in plain language.
- Never reach outside the map. Whether an unmatched need may be built at all is not your call —
that boundary (including the conservative-match rule and the fail-closed behaviour when the map
is missing or malformed) belongs to the
allowed-stack-guardrailskill, which runs before anything is built. This skill only ever selects from the map.
The procedure
- Elicit needs, not technologies. Draw out the outcome, the audience, and the workflow with questions the user can answer without technical vocabulary. If the user does name a technology, translate it back to the need behind it ("what should that let your visitors do?") rather than adopting it as a requirement.
- Map behind the scenes. Select the building block(s) whose Good for purposes cover the need. Prefer the smallest set of blocks that serves the whole workflow; note (internally) which rows you matched so the guardrail check and any later redirect are grounded in the same rows.
- Confirm behaviour, not design. Play the plan back as product behaviour ("here's what your visitors will experience …") and get a plain-language yes before building. The user approves described behaviour, never an architecture.
- Apply conventions silently. Build the deployment's way — its scaffolds, its quality gates, its delivery process — without discussing any of it. Conventions are applied, not taught; they surface in conversation only if the user asks how things work (glossary indirection).
- Report outcomes. Progress and completion are reported as product outcomes in the user's vocabulary, per the voice skill.
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.
- yesterday First seen · 62 lines · 109 tokens per session scan A 4acc74fb1d36
needs-stack-mapping is a skill published in the GitHub repository devantler-tech/agent-plugins (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 109 tokens to every session and 952 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
planning-with-files-ar
تخطيط مستمر قائم على الملفات لعمل وكلاء الذكاء الاصطناعي متعدد الخطوات. يحتفظ بملفات taskplan.md و findings.md و progress.md على القرص، وتحقن خطافات دورة الحياة سياق التخطيط المحدد للمشروع. تقرأ الاستعادة التلقائية ملفات تخطيط المشروع فقط. يمكن للأمر الصريح session-catchup.py --metadata فحص بيانات وصفية لجلسات الوكيل…
kl-consistency-test
Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a…
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
dsh-web-documentation
Use when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.