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 commands/amusleh-spotware-com/terse-sharp/sync-docsgit clone --depth 1 https://github.com/amusleh-spotware-com/terse-sharpWrote 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/amusleh-spotware-com/terse-sharp/sync-docs)<a href="https://agentmods.dev/commands/amusleh-spotware-com/terse-sharp/sync-docs"><img src="https://agentmods.dev/badge/commands/amusleh-spotware-com/terse-sharp/sync-docs.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 | $0.00036 | $0.03580 |
| Opus 5 | $0.00018 | $0.01790 |
| Sonnet 5 | $0.00007 | $0.00716 |
| Haiku 4.5 | $0.00004 | $0.00358 |
Grade A, and why
sync-docs 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 3d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🚫 HARD GATE — the docs are part of the tool surface. Sync them from the code, not from memory.
README.md is what a user reads before installing, NUGET_README.md is what nuget.org renders, and
src/TerseSharp.Server/Assets/SKILL.md is an embedded resource shipped by terse install --skill
and loaded straight into an agent's context — a tool it does not name might as well not exist, and
a response format it describes the old way is worse than no skill. This command makes all three,
plus CLAUDE.md and the rest, true again.
$ARGUMENTS — if it names a document, check that one first; every other document is still checked.
Nothing else takes input from the user.
Banned for the whole run:
AskUserQuestion,ExitPlanMode, "shall I continue?", handing work back. Autonomous from P0 to P8.- Spawning any subagent. No
Agentcall, noWorkflow, nocode-review-gateR2a reviewer, nocaveman:*reviewer. This run's deliverable is documents; the arbiter is the census tests in P6 plus the written self-check in P7. That is a deliberate, user-stated exception to the standing reviewer rule, and it holds only while the change set is documents. - Editing any
.cs,.csproj,.props,.targets,.slnx,.resx,.xamlor.razorfile. When a document and the code disagree, the code wins and the document changes. If the code is what is wrong, log it as a row inIMPROVEMENTS.md## Open(never in the archive) and say so in P8 — do not fix it here. A code edit in this run voids the no-reviewer exception above. Read/Grep/Glob/Edit/Write, andBash: git status,git diff,grep,rg,cat,head,tail,sed,awk,ls,find,dotnet build,dotnet test. All of those are terse-sharp calls. Only git history, index/history mutation (add,commit,push) andghstay onBash.- Answering from the connected
terseMCP server about how a tool behaves. It is whateverdotnet tool install/updatelast put on PATH — notHEAD. Three sessions have been spent arguing with docs written against a three-release-old binary. Evidence order: an E2E test against the freshly builtterse.dll> a hand-rundotnet run --project src/TerseSharp.Server -- serve …> current source read withget_symbol_source. Say which one answered. git add -A/git commit -am. Stage by path — this tree is shared with other sessions and with.claude/worktrees/agent-*.- A
Co-Authored-By:trailer. - Rewriting a document from memory. Every edit is
edit_text section="## Heading"or anoldTexttaken from a read in this run — a remembered anchor is the 102-InvalidArgumenttrap.
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.
- 3d ago First seen · 210 lines · 36 tokens per session scan A 8655a419360e
sync-docs is a command published in the GitHub repository amusleh-spotware-com/terse-sharp (2 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 3,580 once invoked, about $0.0002 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 commands, from other repositories
pre-commit
Before running the checklist, run git fetch origin. If the current branch is behind origin/master, stop and rebase before proceeding.
commit
Create a Conventional Commit with signoff.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
changelog
Summarize staged git changes into a concise changelog/commit message.
help
Lists available commands or provides detailed help on a specific command.
merge
Merge branches with auto-generated Conventional Commits message.