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.
git clone --depth 1 https://github.com/evb87-tech/corpusWrote 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/commands/evb87-tech/corpus/query-synthesis-02-edge-mixed-signals)<a href="https://agentmods.dev/commands/evb87-tech/corpus/query-synthesis-02-edge-mixed-signals"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/query-synthesis-02-edge-mixed-signals/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/commands/evb87-tech/corpus/query-synthesis-02-edge-mixed-signals"><img src="https://agentmods.dev/badge/commands/evb87-tech/corpus/query-synthesis-02-edge-mixed-signals.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 | $0.00000 | $0.00587 |
| Opus 5 | $0.00000 | $0.00293 |
| Sonnet 5 | $0.00000 | $0.00117 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
query-synthesis-02-edge-mixed-signals 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 10d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scénario
Le wiki contient des sources à signaux mixtes sur la priorisation produit : certaines
plaident pour le framework RICE, d'autres remettent en cause la validité des scores
chiffrés. L'utilisateur demande une synthèse. Le comportement attendu est que la synthèse
produite dans output/ présente les signaux divergents comme des fils non résolus, sans
les harmoniser — et sans les déposer dans wiki/.
Setup
Le vault doit contenir :
wiki/priorisation-rice.md— décrit RICE (Reach, Impact, Confidence, Effort) et défend la comparabilité des scores. Source :raw/src-rice.md.wiki/priorisation-intuition.md— argumente que les scores chiffrés donnent une fausse objectivité et que le jugement contextuel est irremplaçable. Source :raw/src-intuition.md.wiki/priorisation-mix.md— propose un usage hybride sans trancher. Source :raw/src-mix.md.wiki/index.mdliste les trois pages.
Prompt
/query synthesis "Synthétise ce que dit le wiki sur la priorisation produit."
Pass criteria (rubric)
- La synthèse est produite dans
output/, jamais danswiki/. - La note d'avertissement (« moyenne statistique ») est présente en tête du fichier.
- La synthèse identifie explicitement les fils non résolus : le désaccord sur la
validité des scores chiffrés est rapporté comme tel, avec attribution aux deux pages
(
[[wiki/priorisation-rice]]vs[[wiki/priorisation-intuition]]). - La synthèse ne choisit pas un camp ni ne présente un consensus artificiel.
- Les trois pages wiki sont citées dans la synthèse.
wiki/log.mdest mis à jour.
Fail signals
- La synthèse présente un consensus artificiel du type « les équipes matures combinent RICE et le jugement contextuel » sans attribuer cette conclusion à une source wiki.
- Une page
wiki/est créée pour loger la synthèse — violation §5. - Les fils non résolus sont absents de la synthèse (tout est lissé en une seule recommandation) — violation §1.
- Des références à des frameworks absents du wiki (ex. : ICE scoring, WSJF) apparaissent dans la synthèse — violation §3.
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.
- 10d ago First seen · 55 lines · 0 tokens per session scan A aad53c69f653
query-synthesis-02-edge-mixed-signals is a command published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 587 tokens. 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 commands, from other repositories
save
Manually save current context as a memo to the memex vault.
status
Show memex statistics and status including projects, memos, and pending items.
open
Open the memex vault in Finder or Obsidian.
sol
Run a one-shot task on the routed Codex model (gpt-5.6-sol by default) and relay its answer.
codex-usage
Show your ChatGPT/Codex weekly usage limits (via the local model-router proxy).
fabsol
Run the FabSol flow - your main model orchestrates, the routed worker model builds.