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 skills add alphabravo-oss/guild --skill tempergit clone --depth 1 https://github.com/alphabravo-oss/guildWrote 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/alphabravo-oss/guild/temper)<a href="https://agentmods.dev/skills/alphabravo-oss/guild/temper"><img src="https://agentmods.dev/badge/skills/alphabravo-oss/guild/temper/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/skills/alphabravo-oss/guild/temper"><img src="https://agentmods.dev/badge/skills/alphabravo-oss/guild/temper.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 | $0.00055 | $0.06205 |
| Opus 5.5 | $0.00022 | $0.02482 |
| Sonnet 5.5 | $0.00011 | $0.01241 |
| Haiku 4.5 | $0.00006 | $0.00620 |
Grade A, and why
temper 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 1mo 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 — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foundry integration: This skill's methodology is used as F5 TEMPER in Foundry runs invoked with
--temper. When invoked by Foundry, temper domains and probe results are written tofoundry-archive/{run}/temper/.
Temper — Micro-Domain Deep Audit
Temper activates after F4 ASSAY terminates. What terminates ASSAY is the tier-aware gates,
not a count of every finding ever filed: ASSAY passes when no LIVE defect and no
unknown-tier defect is open, and an open backlog of the non-blocking tiers, LATENT and
HARDENING alike, does not hold it shut — the same rule that ends temper itself, stated
once more under When the sweep ends below. Broad
audits miss things because they look at too much at once. Temper zooms into the smallest units of
functionality and proves they work — or proves they don't.
Mindset: Bug Hunter, Not Reviewer
Your job is to FIND what's broken. Assume every function has a bug until you prove otherwise by reading the body line by line. If you finish with zero findings, you failed — re-read the 5 most complex functions and run the checklist again.
Phase C0: ROSTER — read the recorded candidates BEFORE anything else
Your first tool call is Foundry-Observations(classification="TEMPER_CANDIDATE"). Those
records are the probe ideas the PROVE stream had at INSPECT and was forbidden to file: on a
run with --temper set, an INSPECT defect must cite the matrix row whose stated behaviour
failed, and every off-row hunch is recorded as a candidate instead of spent as a GRIND cycle.
TEMPER is the phase those hunches were being saved FOR. Read them before you build anything,
because a candidate you never read is a probe the run paid to think of and then threw away.
Your roster is the open candidates UNIONED with your own micro-domains, never one or the
other. Phase C1 below discovers domains from the filesystem and stays spec-blind; this read
does not break that, and the reason is mechanical rather than a promise: a TEMPER_CANDIDATE
observation carries no spec_ref and no requirement id at all — Foundry-Observation refuses
one that does, reading any spec_ref as a spec-required-behaviour claim by construction — so
a candidate tells you a place to look and nothing about what the spec says should be there.
Walk the filesystem in C1 without narrowing it to the candidate list, then add every open
candidate to the domains that walk produced.
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.
- 1mo ago Changed · +6 lines 3bb8c4ba63f9
- 1mo ago Changed · +119 lines e776025309f4
- 1mo ago First seen · 267 lines · 55 tokens per session scan A 44e127a714a2
temper is a skill published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 11d ago), licensed MIT. It adds 55 tokens to every session and 6,205 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…