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/allenc84/sapience/lognpx skills add allenc84/sapience --skill loggit clone --depth 1 https://github.com/allenc84/sapienceWrote 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/allenc84/sapience/log)<a href="https://agentmods.dev/skills/allenc84/sapience/log"><img src="https://agentmods.dev/badge/skills/allenc84/sapience/log.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 | $0.00024 | $0.01197 |
| Opus 5 | $0.00012 | $0.00598 |
| Sonnet 5 | $0.00005 | $0.00239 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
log 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 4d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/log — Judgment Ledger Command
Usage:
/sapience:log <description>— log a new assessment from natural language/sapience:log review— show all pending assessments/sapience:log review <domain>— show pending for one domain (one of your configuredLEDGER_DOMAINS)/sapience:log resolve <id>— score a specific assessment by ID/sapience:log calibration <domain>— generate calibration pattern from resolved assessments in a domain (requires 3+ binary-scored — partial resolutions don't count)/sapience:log bias— generate cross-domain bias map
Routing
Read $ARGUMENTS and route to the correct behavior below.
NEW ASSESSMENT: /sapience:log <description>
If $ARGUMENTS is non-empty and does not start with review, resolve, calibration, or bias:
Extract the following from the natural language description:
- text: The assessment or prediction, stated clearly and specifically. Include prices, names, quantities.
- domain: One of the configured
LEDGER_DOMAINS. Infer from context which domain the assessment belongs to; if none fits cleanly, pick the closest and note the inference in the confirmation. - probability: a number 0-1 for how likely the call is to prove right (e.g.
0.7). Prefer this — it's what makes calibration (Brier score) real. Extract it if the user gives odds/percentages; otherwise fall back to confidence (high/moderate/low, defaultmoderate), which maps to 0.9/0.75/0.6. - horizon: e.g. "3 months", "2 weeks", "end of Q3". Infer from context. Leave blank if not determinable.
- logic: The reasoning behind the call at this moment. Pull from context or ask the user if unclear.
- conditions: Relevant conditions — price levels, team state, market context, etc.
Call mcp__sapience__log_assessment with the extracted fields. Then confirm back:
Logged: [text] | [domain] | [confidence] | horizon: [horizon] | ID: [id]
If the input is ambiguous (domain unclear, no horizon, logic missing), make reasonable inferences and note them in the confirmation rather than asking.
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.
- 4d ago First seen · 109 lines · 24 tokens per session scan A 530d065c0fcc
log is a skill published in the GitHub repository allenc84/sapience (0 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 1,197 once invoked, about $0.0001 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
grill-agent
The AUTOMATED counterpart of /mneme:grill: the same interviewer discipline (a visible branch tree, doses of questions, a protocol finale), but FACT questions are answered by a RESPONDENT — a fresh Task spawn per round, grounded in the code — instead of the user. The user answers only DECISIONS. This automates the…
setup
The ENTRY for a new user or a new project. One run per repository: diagnose the ALREADY WIRED mneme surface with zero questions, render one ternary report, offer ONLY the applicable fixes — each behind its own digit — then walk the FIRST note through the human staging gate so the remember → human gate → recall loop is…
grill
The INTERROGATOR of the lineup: arch thinks, plan proposes, dev executes — grill EXTRACTS. It takes a raw, under-formulated idea and asks questions in small doses, round after round, keeping a visible map of the decision tree (closed vs open branches), until the USER says the tree is closed. Then — and only then — it…
migrate
convert an externally-authored spec into runnable workflow phase files and render the graph map with boundary candidates, without running anything.
resume
Read-only ORIENTATION. It reads the current git branch, finds the branch's active run in mneme's event log, reconstructs the phase map (closed / ready / blocked / paused-on-boundary) plus the staged-but-unaccepted notes, and SUGGESTS the /mneme:dev continuation in REAL syntax — slug + until, with boundary candidates…
arch
Read-only architecture analysis — 2-3 solutions with trade-offs, one recommended. Use when designing a component or scoping a refactor.