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/tessaryai/plugins/derive-sopnpx skills add tessaryai/plugins --skill derive-sopgit clone --depth 1 https://github.com/tessaryai/pluginsWrote 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/tessaryai/plugins/derive-sop)<a href="https://agentmods.dev/skills/tessaryai/plugins/derive-sop"><img src="https://agentmods.dev/badge/skills/tessaryai/plugins/derive-sop.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 | $0.00106 | $0.02800 |
| Opus 5 | $0.00053 | $0.01400 |
| Sonnet 5 | $0.00021 | $0.00560 |
| Haiku 4.5 | $0.00011 | $0.00280 |
Grade A, and why
derive-sop 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
derive-sop — distill a call site's instructions into a v3 SOP
The platform runs an SOP-conformance classifier: it watches a call site's production traffic
and reports when the agent drifts from its own standing procedure. The customer-side artifact that
feeds it is one v3 SOP file per call site — seven concepts, authored here, kept true by
/evals:reconcile-sop:
agent: <call-site id> # the tessary.call_site.id, verbatim
intents: # demand-side: what the USER comes for
<intent-id>:
means: "<one sentence of demand-side meaning>"
observations: # the vocabulary: agent acts, member acts, world-states
<obs-id>: "<one atomic sentence>"
<obs-id>: # optional frame-exemplar form (judgement observations)
is: "<one atomic sentence>"
counts: # 2–3 adjudicated mini-scenarios TOTAL across both lists
- "<a scenario this observation covers>"
counts_not:
- "<a near-miss it does not cover>"
rules:
- in: <intent-id | [ids] | any> # owed-scope
when: <obs-id> # optional trigger
unless: <obs-id> # optional negated condition
at: <session-start | session-end> # optional positional anchor
expect: <obs-id | {tool: t, before: it|t2, paired_by: k, within: conversation|turn}>
# — or —
never: <obs-id | {tool: t}>
# optional: either: [a, b] (alternative satisfaction) · of: <delegate-role> (orchestrators)
Pure meaning, zero mechanism. No detectors, thresholds, regexes, label files, file paths, line
numbers, or provenance anchors — ever. Routing, detector synthesis, and bindings are compiled
server-side by the platform; nothing mechanical belongs in the customer's repo, and nothing in
this file may assume how it will be measured. The schema and its measured basis live in the
evals-platform repo's classifiers/experiments/SCHEMA-V3.md; the short version: the repo's own
instruction text routes and compiles most observations on its own, and the frame conventions
exemplars carry are the measured remainder.
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 · 200 lines · 106 tokens per session scan A 15d5586ef4e8
derive-sop is a skill published in the GitHub repository tessaryai/plugins (3 stars, last pushed 3d ago), licensed MIT. It adds 106 tokens to every session and 2,800 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
ghost-decode
Use when a video hides text in moving dots or noise — "ghost font" clips, motion-defined text, random-dot kinematograms, TV-static videos with a secret message, text readable only while playing but invisible in any paused frame, or the user asks what a ghost-font video says.
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.