Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add tessaryai/plugins/plugin install evalsWrote 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/reconcile-sop)<a href="https://agentmods.dev/skills/tessaryai/plugins/reconcile-sop"><img src="https://agentmods.dev/badge/skills/tessaryai/plugins/reconcile-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 5.1 | $0.00099 | $0.01424 |
| Opus 5 | $0.00049 | $0.00712 |
| Sonnet 5 | $0.00020 | $0.00285 |
| Haiku 4.5 | $0.00010 | $0.00142 |
Grade A, and why
reconcile-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 8d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reconcile-sop — keep the SOP true as the code changes
A v3 SOP (.tessary/sops/<call_site_id>.yaml, authored by /evals:derive-sop) states what a call
site's standing procedure means. Commits change prompts, tool descriptions, and routing — and a
conformance file that has drifted from its own instruction surface measures the wrong thing while
looking authoritative. This skill is the maintenance half of the contract: re-read, re-verify every
sentence, propose changes, re-lint.
There are no stored anchors, by design. The SOP deliberately carries no file paths, line numbers, or quoted prompt text to check against — pointers rot the moment a prompt file is refactored, and instructions live duplicated and disjoint across real repos (this platform's own git-observer learned the same lesson and moved from static anchors to re-analysis). So reconciliation is never "check the anchors": it is re-derive the rule↔code correspondence by reading the whole instruction surface, every time. Evidence lives transiently in your change proposal, never in the file.
Resolve the plugin path once
PLUGIN="${CLAUDE_PLUGIN_ROOT:-$(find ~/.claude -name SKILL.md -path '*/evals/skills/reconcile-sop/*' 2>/dev/null \
| xargs -I{} dirname {} | xargs -I{} dirname {} | xargs -I{} dirname {} \
| sort -V | tail -1)}"
echo "PLUGIN=$PLUGIN"
Flow
1 — Locate the SOPs in scope
List .tessary/sops/**/*.yaml. If the user named a call site or a commit range, scope to the SOPs
plausibly touched; with no hint, reconcile all of them. No SOPs → route to /evals:derive-sop.
A recent diff (git log/git diff over prompt and tool files) tells you where to look first —
never what to skip: an instruction can change meaning through an edit far from where it was
first stated.
2 — Re-read the whole instruction surface
Exactly as /evals:derive-sop step 2: system prompts and their composed fragments, tool
definitions and descriptions, routing rules, few-shot examples, guardrail config, checked-in
policy documents — all copies, however duplicated or disjoint. This is a full re-read, not a
delta-read; the absence of anchors is what makes that mandatory, and it is what makes the result
trustworthy.
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.
- 8d ago First seen · 107 lines · 99 tokens per session scan A e335e01341ea
reconcile-sop is a skill published in the GitHub repository tessaryai/plugins (3 stars, last pushed 7d ago), licensed MIT. It adds 99 tokens to every session and 1,424 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.
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.
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…
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.