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 anotb/driftglass --skill answer-missiongit clone --depth 1 https://github.com/anotb/driftglassWrote 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/anotb/driftglass/answer-mission)<a href="https://agentmods.dev/skills/anotb/driftglass/answer-mission"><img src="https://agentmods.dev/badge/skills/anotb/driftglass/answer-mission/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/anotb/driftglass/answer-mission"><img src="https://agentmods.dev/badge/skills/anotb/driftglass/answer-mission.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 | $0.00060 | $0.01791 |
| Opus 5.5 | $0.00024 | $0.00716 |
| Sonnet 5.5 | $0.00012 | $0.00358 |
| Haiku 4.5 | $0.00006 | $0.00179 |
Grade A, and why
answer-mission 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 2mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Answer from Driftglass
Use Driftglass as the evidence source. Do not answer from general memory when the connected instance is available. Choose one route.
Shape the live card
Answer the user's question with the information that changes the answer. Do not write a changelog, source recap, or status report.
- Default to
answerMode: synthesisfor questions about state, trajectory, causes, implications, comparison, or what changed broadly. - In synthesis mode, start with a required cited
thesisthat gives the answer and causal spine. Stop when the question is answered; do not pad it to fill a format. It may stand alone. Add one to fourkeyJudgments, an optionalcompetingExplanation, and zero to twowatchForsignals only when each extra block adds a distinct fact, mechanism, implication, or falsifier. Give every included judgment a factualtitleand concrete evidence. Omit every extra block that does not add one. - Use
answerMode: decisiononly when the user explicitly asks for a choice, action, test, deferral, or rollback rule. Provide citedwhatChangedandwhyItMatters, then include exactly the requesteddecisionrows: a boundedtestNowwith comparison and sample or timebox, an observabledeferUntilcondition, and/or a measurablerollbackIfthreshold with its evaluation window. A generic recommendation gets only the single most relevant row. These parameters are ChatGPT judgment anchored by cited evidence, not claims that a source states them verbatim. Do not add synthesis fields orwatchNextin decision mode. - Lead with claims. Prefer dates, quantities, mechanisms, and consequences to adjectives or stacked qualifiers. Connect developments only when the evidence supports the connection.
- Every rendered section needs one to three exact public citation URLs from the evidence result. Keep URLs out of prose and put them in that section's
citationUrls. - Do not narrate source counts, source families, coverage, evidence mechanics, tools, receipts, or the briefing process in answer fields. Keep limits in the collapsed source disclosure.
- After
present_briefsucceeds, stop. The live card is the answer, so do not add a prose recap or generic conclusion.
What ships with it
1 file 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.
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.
- 2mo ago First seen · 73 lines · 60 tokens per session scan A 634c170a3863
answer-mission is a skill published in the GitHub repository anotb/driftglass (0 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 1,791 once invoked, about $0.0002 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 2026-08-31.
answer-mission compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| answer-missionanotb/driftglass | Skill | 0 | 4d ago | MIT | A | 60 | Codex |
| owd-albatrossmsinclair25/mdevolved | Skill | 2 | 13d ago | Apache-2.0 | A | 93 | Codex |
| owd-evemsinclair25/mdevolved | Skill | 2 | 13d ago | Apache-2.0 | A | 90 | Codex |
| owd-obsidian-mindmsinclair25/mdevolved | Skill | 2 | 13d ago | Apache-2.0 | A | 100 | Codex |
| mdevolved-albatrossmsinclair25/mdevolved | Skill | 2 | 13d ago | Apache-2.0 | A | 36 | Codex |
| mdevolved-evemsinclair25/mdevolved | Skill | 2 | 13d ago | Apache-2.0 | A | 36 | Codex |
| mdevolved-obsidian-mindmsinclair25/mdevolved | Skill | 2 | 13d ago | Apache-2.0 | A | 40 | Codex |