Borrowing it
Nothing to install: this file belongs to Gixsy95/abap_wiki. 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/Gixsy95/abap_wiki/main/.agents/skills/capture-answer/SKILL.mdgit clone --depth 1 https://github.com/Gixsy95/abap_wikiWrote 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/gixsy95/abap_wiki/capture-answer)<a href="https://agentmods.dev/skills/gixsy95/abap_wiki/capture-answer"><img src="https://agentmods.dev/badge/skills/gixsy95/abap_wiki/capture-answer.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 | $0.00088 | $0.00841 |
| Opus 5 | $0.00044 | $0.00420 |
| Sonnet 5 | $0.00018 | $0.00168 |
| Haiku 4.5 | $0.00009 | $0.00084 |
Grade A, and why
capture-answer 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 7d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture-answer - ingesting expert answers
The expert's answers close the residual load-bearing gaps that auto-research could not
verify. They become canonical expert-answers (slices/<id>/inputs/expert-answers/),
citable with cite-back in the functional sections; if they contradict the code they are marked
[ANOMALY] (the raw/ source is never touched).
Procedure
-
Collect the answers. The expert has filled in the Expert answer blocks in the file
slices/<id>/interviews/<date>-<slice>-<dest>.md, or has answered verbally. For each answer, identify thegap_idit refers to (these appear in the title of each questionnaire question, e.g.example-slice-g003). -
Build the YAML payload
output/l2/<slice-id>/answers-<date>.yaml:expert: [email protected] scope: "Trigger and purpose of the custom process" kind: clarification # clarification | confirmation | correction | sign-off answers: - gaps: [example-slice-g001] text: | The program ZPROGRAM_BATCH feeds a business data flow used by the custom process for daily operational checks. - gaps: [example-slice-g003] text: | Launched by the batch job ZEXAMPLE_JOB_DAILY via an external scheduler, with an example technical schedule and variant. - gaps: [example-slice-g007] anomaly: true # the answer contradicts the code: mark [ANOMALY] text: | The flag ZZSTATUS='X' should exclude returns, but the code includes it: known bug.A single
textcan answer multiple related gaps (gaps: [g1, g2]). -
Ingest:
.venv/Scripts/python core/src/tools/pipeline.py capture-answer --slice <slice-id> --file output/l2/<slice-id>/answers-<date>.yamlCreates
slices/<id>/inputs/expert-answers/<date>-<slug>.md, moves the gaps toanswered(withresolution_refpointing to the expert-answer), closes thequestionsand records the evidence (source: expert). Regeneratesgaps.yaml.
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.
- 7d ago First seen · 65 lines · 88 tokens per session scan A 6855771b4867
capture-answer is a skill published in the GitHub repository Gixsy95/abap_wiki (44 stars, last pushed 6d ago), licensed MIT. It adds 88 tokens to every session and 841 once invoked, about $0.0004 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
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-health
Use at the start of Link work when readiness is unclear, after installs or upgrades, and before repairs; verify health, inspect interrupted writes, back up, and repair generated indexes without MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.
ingest
Populate the gnosis-mcp knowledge base — from local files, git history, or a crawled website. Handles the full matrix of flags (--force, --prune, --wipe, --embed, --include-crawled) in one place.
manage
CRUD operations on the knowledge base — add, delete, update metadata. For bulk ingest / re-ingest / prune, use /gnosis:ingest instead. Requires GNOSISMCPWRITABLE=true.